To see the other types of publications on this topic, follow the link: Graph and Multi-view Memory Attention.
Journal articles on the topic 'Graph and Multi-view Memory Attention'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Graph and Multi-view Memory Attention.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Ai, Bing, Yibing Wang, Liang Ji, Jia Yi, Ting Wang, Wentao Liu, and Hui Zhou. "A graph neural network fused with multi-head attention for text classification." Journal of Physics: Conference Series 2132, no. 1 (December 1, 2021): 012032. http://dx.doi.org/10.1088/1742-6596/2132/1/012032.
Full textAbstract:
Abstract Graph neural network (GNN) has done a good job of processing intricate architecture and fusion of global messages, research has explored GNN technology for text classification. However, the model that fixed the entire corpus as a graph in the past faced many problems such as high memory consumption and the inability to modify the construction of the graph. We propose an improved model based on GNN to solve these problems. The model no longer fixes the entire corpus as a graph but constructs different graphs for each text. This method reduces memory consumption, but still retains global information. We conduct experiments on the R8, R52, and 20newsgroups data sets, and use accuracy as the experimental standard. Experiments show that even if it consumes less memory, our model accomplish higher than existing models on multiple text classification data sets.
2
Liu, Di, Hui Xu, Jianzhong Wang, Yinghua Lu, Jun Kong, and Miao Qi. "Adaptive Attention Memory Graph Convolutional Networks for Skeleton-Based Action Recognition." Sensors 21, no. 20 (October 12, 2021): 6761. http://dx.doi.org/10.3390/s21206761.
Full textAbstract:
Graph Convolutional Networks (GCNs) have attracted a lot of attention and shown remarkable performance for action recognition in recent years. For improving the recognition accuracy, how to build graph structure adaptively, select key frames and extract discriminative features are the key problems of this kind of method. In this work, we propose a novel Adaptive Attention Memory Graph Convolutional Networks (AAM-GCN) for human action recognition using skeleton data. We adopt GCN to adaptively model the spatial configuration of skeletons and employ Gated Recurrent Unit (GRU) to construct an attention-enhanced memory for capturing the temporal feature. With the memory module, our model can not only remember what happened in the past but also employ the information in the future using multi-bidirectional GRU layers. Furthermore, in order to extract discriminative temporal features, the attention mechanism is also employed to select key frames from the skeleton sequence. Extensive experiments on Kinetics, NTU RGB+D and HDM05 datasets show that the proposed network achieves better performance than some state-of-the-art methods.
3
Feng, Aosong, Irene Li, Yuang Jiang, and Rex Ying. "Diffuser: Efficient Transformers with Multi-Hop Attention Diffusion for Long Sequences." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 11 (June 26, 2023): 12772–80. http://dx.doi.org/10.1609/aaai.v37i11.26502.
Full textAbstract:
Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity. Sparse Transformer is a popular approach to improving the efficiency of Transformers by restricting self-attention to locations specified by the predefined sparse patterns. However, leveraging sparsity may sacrifice expressiveness compared to full-attention, when important token correlations are multiple hops away. To combine advantages of both the efficiency of sparse transformer and the expressiveness of full-attention Transformer, we propose Diffuser, a new state-of-the-art efficient Transformer. Diffuser incorporates all token interactions within one attention layer while maintaining low computation and memory costs. The key idea is to expand the receptive field of sparse attention using Attention Diffusion, which computes multi-hop token correlations based on all paths between corresponding disconnected tokens, besides attention among neighboring tokens. Theoretically, we show the expressiveness of Diffuser as a universal sequence approximator for sequence-to-sequence modeling, and investigate its ability to approximate full-attention by analyzing the graph expander property from the spectral perspective. Experimentally, we investigate the effectiveness of Diffuser with extensive evaluations, including language modeling, image modeling, and Long Range Arena (LRA). Evaluation results show that Diffuser achieves improvements by an average of 0.94% on text classification tasks and 2.30% on LRA, with 1.67x memory savings compared to state-of-the-art benchmarks, which demonstrates superior performance of Diffuser in both expressiveness and efficiency aspects.
4
Li, Mingxiao, and Marie-Francine Moens. "Dynamic Key-Value Memory Enhanced Multi-Step Graph Reasoning for Knowledge-Based Visual Question Answering." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (June 28, 2022): 10983–92. http://dx.doi.org/10.1609/aaai.v36i10.21346.
Full textAbstract:
Knowledge-based visual question answering (VQA) is a vision-language task that requires an agent to correctly answer image-related questions using knowledge that is not presented in the given image. It is not only a more challenging task than regular VQA but also a vital step towards building a general VQA system. Most existing knowledge-based VQA systems process knowledge and image information similarly and ignore the fact that the knowledge base (KB) contains complete information about a triplet, while the extracted image information might be incomplete as the relations between two objects are missing or wrongly detected. In this paper, we propose a novel model named dynamic knowledge memory enhanced multi-step graph reasoning (DMMGR), which performs explicit and implicit reasoning over a key-value knowledge memory module and a spatial-aware image graph, respectively. Specifically, the memory module learns a dynamic knowledge representation and generates a knowledge-aware question representation at each reasoning step. Then, this representation is used to guide a graph attention operator over the spatial-aware image graph. Our model achieves new state-of-the-art accuracy on the KRVQR and FVQA datasets. We also conduct ablation experiments to prove the effectiveness of each component of the proposed model.
5
Jung, Tae-Won, Chi-Seo Jeong, In-Seon Kim, Min-Su Yu, Soon-Chul Kwon, and Kye-Dong Jung. "Graph Convolutional Network for 3D Object Pose Estimation in a Point Cloud." Sensors 22, no. 21 (October 25, 2022): 8166. http://dx.doi.org/10.3390/s22218166.
Full textAbstract:
Graph Neural Networks (GNNs) are neural networks that learn the representation of nodes and associated edges that connect it to every other node while maintaining graph representation. Graph Convolutional Neural Networks (GCNs), as a representative method in GNNs, in the context of computer vision, utilize conventional Convolutional Neural Networks (CNNs) to process data supported by graphs. This paper proposes a one-stage GCN approach for 3D object detection and poses estimation by structuring non-linearly distributed points of a graph. Our network provides the required details to analyze, generate and estimate bounding boxes by spatially structuring the input data into graphs. Our method proposes a keypoint attention mechanism that aggregates the relative features between each point to estimate the category and pose of the object to which the vertices of the graph belong, and also designs nine degrees of freedom of multi-object pose estimation. In addition, to avoid gimbal lock in 3D space, we use quaternion rotation, instead of Euler angle. Experimental results showed that memory usage and efficiency could be improved by aggregating point features from the point cloud and their neighbors in a graph structure. Overall, the system achieved comparable performance against state-of-the-art systems.
6
Cui, Wei, Fei Wang, Xin He, Dongyou Zhang, Xuxiang Xu, Meng Yao, Ziwei Wang, and Jiejun Huang. "Multi-Scale Semantic Segmentation and Spatial Relationship Recognition of Remote Sensing Images Based on an Attention Model." Remote Sensing 11, no. 9 (May 2, 2019): 1044. http://dx.doi.org/10.3390/rs11091044.
Full textAbstract:
A comprehensive interpretation of remote sensing images involves not only remote sensing object recognition but also the recognition of spatial relations between objects. Especially in the case of different objects with the same spectrum, the spatial relationship can help interpret remote sensing objects more accurately. Compared with traditional remote sensing object recognition methods, deep learning has the advantages of high accuracy and strong generalizability regarding scene classification and semantic segmentation. However, it is difficult to simultaneously recognize remote sensing objects and their spatial relationship from end-to-end only relying on present deep learning networks. To address this problem, we propose a multi-scale remote sensing image interpretation network, called the MSRIN. The architecture of the MSRIN is a parallel deep neural network based on a fully convolutional network (FCN), a U-Net, and a long short-term memory network (LSTM). The MSRIN recognizes remote sensing objects and their spatial relationship through three processes. First, the MSRIN defines a multi-scale remote sensing image caption strategy and simultaneously segments the same image using the FCN and U-Net on different spatial scales so that a two-scale hierarchy is formed. The output of the FCN and U-Net are masked to obtain the location and boundaries of remote sensing objects. Second, using an attention-based LSTM, the remote sensing image captions include the remote sensing objects (nouns) and their spatial relationships described with natural language. Finally, we designed a remote sensing object recognition and correction mechanism to build the relationship between nouns in captions and object mask graphs using an attention weight matrix to transfer the spatial relationship from captions to objects mask graphs. In other words, the MSRIN simultaneously realizes the semantic segmentation of the remote sensing objects and their spatial relationship identification end-to-end. Experimental results demonstrated that the matching rate between samples and the mask graph increased by 67.37 percentage points, and the matching rate between nouns and the mask graph increased by 41.78 percentage points compared to before correction. The proposed MSRIN has achieved remarkable results.
7
Hou, Miaomiao, Xiaofeng Hu, Jitao Cai, Xinge Han, and Shuaiqi Yuan. "An Integrated Graph Model for Spatial–Temporal Urban Crime Prediction Based on Attention Mechanism." ISPRS International Journal of Geo-Information 11, no. 5 (April 30, 2022): 294. http://dx.doi.org/10.3390/ijgi11050294.
Full textAbstract:
Crime issues have been attracting widespread attention from citizens and managers of cities due to their unexpected and massive consequences. As an effective technique to prevent and control urban crimes, the data-driven spatial–temporal crime prediction can provide reasonable estimations associated with the crime hotspot. It thus contributes to the decision making of relevant departments under limited resources, as well as promotes civilized urban development. However, the deficient performance in the aspect of the daily spatial–temporal crime prediction at the urban-district-scale needs to be further resolved, which serves as a critical role in police resource allocation. In order to establish a practical and effective daily crime prediction framework at an urban police-district-scale, an “online” integrated graph model is proposed. A residual neural network (ResNet), graph convolutional network (GCN), and long short-term memory (LSTM) are integrated with an attention mechanism in the proposed model to extract and fuse the spatial–temporal features, topological graphs, and external features. Then, the “online” integrated graph model is validated by daily theft and assault data within 22 police districts in the city of Chicago, US from 1 January 2015 to 7 January 2020. Additionally, several widely used baseline models, including autoregressive integrated moving average (ARIMA), ridge regression, support vector regression (SVR), random forest, extreme gradient boosting (XGBoost), LSTM, convolutional neural network (CNN), and Conv-LSTM models, are compared with the proposed model from a quantitative point of view by using the same dataset. The results show that the predicted spatial–temporal patterns by the proposed model are close to the observations. Moreover, the integrated graph model performs more accurately since it has lower average values of the mean absolute error (MAE) and root mean square error (RMSE) than the other eight models. Therefore, the proposed model has great potential in supporting the decision making for the police in the fields of patrolling and investigation, as well as resource allocation.
8
Mi, Chunlei, Shifen Cheng, and Feng Lu. "Predicting Taxi-Calling Demands Using Multi-Feature and Residual Attention Graph Convolutional Long Short-Term Memory Networks." ISPRS International Journal of Geo-Information 11, no. 3 (March 9, 2022): 185. http://dx.doi.org/10.3390/ijgi11030185.
Full textAbstract:
Predicting taxi-calling demands at the urban area level is vital to coordinate the supply–demand balance of the urban taxi system. Differing travel patterns, the impact of external data, and the expression of dynamic spatiotemporal demand dependence pose challenges to predicting demand. Here, a framework using residual attention graph convolutional long short-term memory networks (RAGCN-LSTMs) is proposed to predict taxi-calling demands. It consists of a spatial dependence (SD) extractor, which extracts SD features; an external dependence extractor, which extracts traffic environment-related features; a pattern dependence (PD) extractor, which extracts the PD of demands for different zones; and a temporal dependence extractor and predictor, which leverages the abovementioned features into an LSTM model to extract temporal dependence and predict demands. Experiments were conducted on taxi-calling records of Shanghai City. The results showed that the prediction accuracies of the RAGCN-LSTMs model were a mean absolute error of 0.8664, a root mean square error of 1.4965, and a symmetric mean absolute percentage error of 43.11%. It outperformed both classical time-series prediction methods and other deep learning models. Further, to illustrate the advantages of the proposed model, we investigated its predicting performance in various demand densities in multiple urban areas and proved its robustness and superiority.
9
Karimanzira, Divas, Linda Ritzau, and Katharina Emde. "Catchment Area Multi-Streamflow Multiple Hours Ahead Forecast Based on Deep Learning." Transactions on Machine Learning and Artificial Intelligence 10, no. 5 (September 29, 2022): 15–29. http://dx.doi.org/10.14738/tmlai.105.13049.
Full textAbstract:
Modeling of rainfall-runoff is very critical for flood prediction studies in decision making for disaster management. Deep learning methods have proven to be very useful in hydrological prediction. To increase their acceptance in the hydrological community, they must be physic-informed and show some interpretability. They are several ways this can be achieved e.g. by learning from a fully-trained hydrological model which assumes the availability of the hydrological model or to use physic-informed data. In this work we developed a Graph Attention Network (GAT) with learnable Adjacency Matrix coupled with a Bi-directional Gated Temporal Convolutional Neural Network (2DGAT-BiLSTM). Physic-informed data with spatial information from Digital Elevation Model and geographical data is used to train it. Besides, precipitation, evapotranspiration and discharge, the model utilizes the catchment area characteristic information, such as instantaneous slope, soil type, drainage area etc. The method is compared to two different current developments in deep learning structures for streamflow prediction, which also utilize all the spatial and temporal information in an integrated way. One, namely Graph Neural Rainfall-Runoff Models (GNRRM) uses timeseries prediction on each node and a Graph Neural Network (GNN) to route the information to the target node and another one called STA-LSTM is based on Spatial and temporal Attention Mechanism and Long Short Term Memory (LSTM) for prediction. The different methods were compared in their performance in predicting the flow at several points of a pilot catchment area. With an average prediction NSE and KGE of 0.995 and 0.981, respectively for 2DGAT-BiLSTM, it could be shown that graph attention mechanism and learning the adjacency matrix for spatial information can boost the model performance and robustness, and bring interpretability and with the inclusion of domain knowledge the acceptance of the models.
10
Wang, Changhai, Jiaxi Ren, and Hui Liang. "MSGraph: Modeling multi-scale K-line sequences with graph attention network for profitable indices recommendation." Electronic Research Archive 31, no. 5 (2023): 2626–50. http://dx.doi.org/10.3934/era.2023133.
Full textAbstract:
<abstract><p>Indices recommendation is a long-standing topic in stock market investment. Predicting the future trends of indices and ranking them based on the prediction results is the main scheme for indices recommendation. How to improve the forecasting performance is the central issue of this study. Inspired by the widely used trend-following investing strategy in financial investment, the indices' future trends are related to not only the nearby transaction data but also the long-term historical data. This article proposes the MSGraph, which tries to improve the index ranking performance by modeling the correlations of short and long-term historical embeddings with the graph attention network. The original minute-level transaction data is first synthesized into a series of K-line sequences with varying time scales. Each K-line sequence is input into a long short-term memory network (LSTM) to get the sequence embedding. Then, the embeddings for all indices with the same scale are fed into a graph convolutional network to achieve index aggregation. All the aggregated embeddings for the same index are input into a graph attention network to fuse the scale interactions. Finally, a fully connected network produces the index return ratio for the next day, and the recommended indices are obtained through ranking. In total, 60 indices in the Chinese stock market are selected as experimental data. The mean reciprocal rank, precision, accuracy and investment return ratio are used as evaluation metrics. The comparison results show that our method achieves state-of-the-art results in all evaluation metrics, and the ablation study also demonstrates that the combination of multiple scale K-lines facilitates the indices recommendation.</p></abstract>
11
Ma, Xinwei, Yurui Yin, Yuchuan Jin, Mingjia He, and Minqing Zhu. "Short-Term Prediction of Bike-Sharing Demand Using Multi-Source Data: A Spatial-Temporal Graph Attentional LSTM Approach." Applied Sciences 12, no. 3 (January 23, 2022): 1161. http://dx.doi.org/10.3390/app12031161.
Full textAbstract:
As a convenient, economical, and eco-friendly travel mode, bike-sharing greatly improved urban mobility. However, it is often very difficult to achieve a balanced utilization of shared bikes due to the asymmetric spatio-temporal user demand distribution and the insufficient numbers of shared bikes, docks, or parking areas. If we can predict the short-run bike-sharing demand, it will help operating agencies rebalance bike-sharing systems in a timely and efficient way. Compared to the statistical methods, deep learning methods can automatically learn the relationship between the inputs and outputs, requiring less assumptions and achieving higher accuracy. This study proposes a Spatial-Temporal Graph Attentional Long Short-Term Memory (STGA-LSTM) neural network framework to predict short-run bike-sharing demand at a station level using multi-source data sets. These data sets include historical bike-sharing trip data, historical weather data, users’ personal information, and land-use data. The proposed model can extract spatio-temporal information of bike-sharing systems and predict the short-term bike-sharing rental and return demand. We use a Graph Convolutional Network (GCN) to mine spatial information and adopt a Long Short-Term Memory (LSTM) network to mine temporal information. The attention mechanism is focused on both temporal and spatial dimensions to enhance the ability of learning temporal information in LSTM and spatial information in GCN. Results indicate that the proposed model is the most accurate compared with several baseline models, the attention mechanism can help improve the model performance, and models that include exogenous variables perform better than the models that only consider historical trip data. The proposed short-term prediction model can be used to help bike-sharing users better choose routes and to help operators implement dynamic redistribution strategies.
12
Lin, Chun, Yijia Xu, Yong Fang, and Zhonglin Liu. "VulEye: A Novel Graph Neural Network Vulnerability Detection Approach for PHP Application." Applied Sciences 13, no. 2 (January 6, 2023): 825. http://dx.doi.org/10.3390/app13020825.
Full textAbstract:
Following advances in machine learning and deep learning processing, cyber security experts are committed to creating deep intelligent approaches for automatically detecting software vulnerabilities. Nowadays, many practices are for C and C++ programs, and methods rarely target PHP application. Moreover, many of these methods use LSTM (Long Short-Term Memory) but not GNN (Graph Neural Networks) to learn the token dependencies within the source code through different transformations. That may lose a lot of semantic information in terms of code representation. This article presents a novel Graph Neural Network vulnerability detection approach, VulEye, for PHP applications. VulEye can assist security researchers in finding vulnerabilities in PHP projects quickly. VulEye first constructs the PDG (Program Dependence Graph) of the PHP source code, slices PDG with sensitive functions contained in the source code into sub-graphs called SDG (Sub-Dependence Graph), and then makes SDG the model input to train with a Graph Neural Network model which contains three stack units with a GCN layer, Top-k pooling layer, and attention layer, and finally uses MLP (Multi-Layer Perceptron) and softmax as a classifier to predict if the SDG is vulnerable. We evaluated VulEye on the PHP vulnerability test suite in Software Assurance Reference Dataset. The experiment reports show that the best macro-average F1 score of the VulEye reached 99% in the binary classification task and 95% in the multi-classes classification task. VulEye achieved the best result compared with the existing open-source vulnerability detection implements and other state-of-art deep learning models. Moreover, VulEye can also locate the precise area of the flaw, since our SDG contains code slices closely related to vulnerabilities with a key triggering sensitive/sink function.
13
Liu, Daizong, Xiaoye Qu, Xing Di, Yu Cheng, Zichuan Xu, and Pan Zhou. "Memory-Guided Semantic Learning Network for Temporal Sentence Grounding." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 1665–73. http://dx.doi.org/10.1609/aaai.v36i2.20058.
Full textAbstract:
Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Although existing methods train well-designed deep networks with large amount of data, we find that they can easily forget the rarely appeared cases during training due to the off-balance data distribution, which influences the model generalization and leads to unsatisfactory performance. To tackle this issue, we propose a memory-augmented network, called Memory-Guided Semantic Learning Network (MGSL-Net), that learns and memorizes the rarely appeared content in TSG task. Specifically, our proposed model consists of three main parts: cross-modal interaction module, memory augmentation module, and heterogeneous attention module. We first align the given video-query pair by a cross-modal graph convolutional network, and then utilize memory module to record the cross-modal shared semantic features in the domain-specific persistent memory. During training, the memory slots are dynamically associated with both common and rare cases, alleviating the forgetting issue. In testing, the rare cases can thus be enhanced by retrieving the stored memories, leading to better generalization. At last, the heterogeneous attention module is utilized to integrate the enhanced multi-modal features in both video and query domains. Experimental results on three benchmarks show the superiority of our method on both effectiveness and efficiency, which substantially improves the accuracy not only on the entire dataset but also on the rare cases.
14
Wu, Jie, Ian G. Harris, and Hongzhi Zhao. "GraphMemDialog: Optimizing End-to-End Task-Oriented Dialog Systems Using Graph Memory Networks." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (June 28, 2022): 11504–12. http://dx.doi.org/10.1609/aaai.v36i10.21403.
Full textAbstract:
Effectively integrating knowledge into end-to-end task-oriented dialog systems remains a challenge. It typically requires incorporation of an external knowledge base (KB) and capture of the intrinsic semantics of the dialog history. Recent research shows promising results by using Sequence-to-Sequence models, Memory Networks, and even Graph Convolutional Networks. However, current state-of-the-art models are less effective at integrating dialog history and KB into task-oriented dialog systems in the following ways: 1. The KB representation is not fully context-aware. The dynamic interaction between the dialog history and KB is seldom explored. 2. Both the sequential and structural information in the dialog history can contribute to capturing the dialog semantics, but they are not studied concurrently. In this paper, we propose a novel Graph Memory Network (GMN) based Seq2Seq model, GraphMemDialog, to effectively learn the inherent structural information hidden in dialog history, and to model the dynamic interaction between dialog history and KBs. We adopt a modified graph attention network to learn the rich structural representation of the dialog history, whereas the context-aware representation of KB entities are learnt by our novel GMN. To fully exploit this dynamic interaction, we design a learnable memory controller coupled with external KB entity memories to recurrently incorporate dialog history context into KB entities through a multi-hop reasoning mechanism. Experiments on three public datasets show that our GraphMemDialog model achieves state-of-the-art performance and outperforms strong baselines by a large margin, especially on datatests with more complicated KB information.
15
Liu, Yuanxin, Delei Tian, and Bin Zheng. "Non-communicating Decentralized Multi-robot Collision Avoidance in Grid Graph Workspace based on Dueling Double Deep Q-Network." Journal of Physics: Conference Series 2456, no. 1 (March 1, 2023): 012015. http://dx.doi.org/10.1088/1742-6596/2456/1/012015.
Full textAbstract:
Abstract This paper designs a motion rule suitable for grid environment and proposes a multi-robot autonomous obstacle avoidance method based on deep reinforcement learning. The training and validation of the method are done under the Stage simulation platform based on ROS operating system. During the training process, the robot uses Lidar to obtain the surrounding state information and generates actions based on the state information to obtain rewards, and the robot is guided by the rewards to optimize the strategy. Based on the D3QN algorithm, a new reward function is designed, a proximity penalty is introduced to reduce the collision between robots, a distance reward is added to guide the robot to complete the task, a step reward is added to improve the efficiency of the robot to complete the task, and an illegal action penalty is added to avoid the robot to choose an illegal action; the input is 5 frames of Lidar data, and in the network structure, the agent can better learn the correlation between the data by introducing Long Short Term Memory(LSTM) layer, and introducing Convolutional Block Attention Module(CBAM), a hybrid attention mechanism to allow the robot to pay more attention to the information of the surrounding robots. By designing experiments, we demonstrate that the learned strategy can effectively guide the robot through obstacle avoidance and complete the task.
16
Su, Guimin, Zimu Zeng, Andi Song, Cong Zhao, Feng Shen, Liangxiao Yuan, and Xinghua Li. "A General Framework for Reconstructing Full-Sample Continuous Vehicle Trajectories Using Roadside Sensing Data." Applied Sciences 13, no. 5 (February 28, 2023): 3141. http://dx.doi.org/10.3390/app13053141.
Full textAbstract:
Vehicle trajectory data play an important role in autonomous driving and intelligent traffic control. With the widespread deployment of roadside sensors, such as cameras and millimeter-wave radar, it is possible to obtain full-sample vehicle trajectories for a whole area. This paper proposes a general framework for reconstructing continuous vehicle trajectories using roadside visual sensing data. The framework includes three modules: single-region vehicle trajectory extraction, multi-camera cross-region vehicle trajectory splicing, and missing trajectory completion. Firstly, the vehicle trajectory is extracted from each video by YOLOv5 and DeepSORT multi-target tracking algorithms. The vehicle trajectories in different videos are then spliced by the vehicle re-identification algorithm fused with lane features. Finally, the bidirectional long-short-time memory model (LSTM) based on graph attention is applied to complete the missing trajectory to obtain the continuous vehicle trajectory. Measured data from Donghai Bridge in Shanghai are applied to verify the feasibility and effectiveness of the framework. The results indicate that the vehicle re-identification algorithm with the lane features outperforms the vehicle re-identification algorithm that only considers the visual feature by 1.5% in mAP (mean average precision). Additionally, the bidirectional LSTM based on graph attention performs better than the model that does not consider the interaction between vehicles. The experiment demonstrates that our framework can effectively reconstruct the continuous vehicle trajectories on the expressway.
17
Hu, Zhangfang, Libujie Chen, Yuan Luo, and Jingfan Zhou. "EEG-Based Emotion Recognition Using Convolutional Recurrent Neural Network with Multi-Head Self-Attention." Applied Sciences 12, no. 21 (November 6, 2022): 11255. http://dx.doi.org/10.3390/app122111255.
Full textAbstract:
In recent years, deep learning has been widely used in emotion recognition, but the models and algorithms in practical applications still have much room for improvement. With the development of graph convolutional neural networks, new ideas for emotional recognition based on EEG have arisen. In this paper, we propose a novel deep learning model-based emotion recognition method. First, the EEG signal is spatially filtered by using the common spatial pattern (CSP), and the filtered signal is converted into a time–frequency map by continuous wavelet transform (CWT). This is used as the input data of the network; then the feature extraction and classification are performed by the deep learning model. We called this model CNN-BiLSTM-MHSA, which consists of a convolutional neural network (CNN), bi-directional long and short-term memory network (BiLSTM), and multi-head self-attention (MHSA). This network is capable of learning the time series and spatial information of EEG emotion signals in depth, smoothing EEG signals and extracting deep features with CNN, learning emotion information of future and past time series with BiLSTM, and improving recognition accuracy with MHSA by reassigning weights to emotion features. Finally, we conducted experiments on the DEAP dataset for sentiment classification, and the experimental results showed that the method has better results than the existing classification. The accuracy of high and low valence, arousal, dominance, and liking state recognition is 98.10%, and the accuracy of four classifications of high and low valence-arousal recognition is 89.33%.
18
Ji, Zhanhao, Guojiang Shen, Juntao Wang, Mario Collotta, Zhi Liu, and Xiangjie Kong. "Multi-Vehicle Trajectory Tracking towards Digital Twin Intersections for Internet of Vehicles." Electronics 12, no. 2 (January 5, 2023): 275. http://dx.doi.org/10.3390/electronics12020275.
Full textAbstract:
Digital Twin (DT) provides a novel idea for Intelligent Transportation Systems (ITS), while Internet of Vehicles (IoV) provides numerous positioning data of vehicles. However, complex interactions between vehicles as well as offset and loss of measurements can lead to tracking errors of DT trajectories. In this paper, we propose a multi-vehicle trajectory tracking framework towards DT intersections (MVT2DTI). Firstly, the positioning data is unified to the same coordinate system and associated with the tracked trajectories via matching. Secondly, a spatial–temporal tracker (STT) utilizes long short-term memory network (LSTM) and graph attention network (GAT) to extract spatial–temporal features for state prediction. Then, the distance matrix is computed as a proposed tracking loss that feeds tracking errors back to the tracker. Through the iteration of association and prediction, the unlabeled coordinates are connected into the DT trajectories. Finally, four datasets are generated to validate the effectiveness and efficiency of the framework.
19
Jin, Yanliang, Jinjin Ye, Liquan Shen, Yong Xiong, Lele Fan, and Qingfu Zang. "Hierarchical Attention Neural Network for Event Types to Improve Event Detection." Sensors 22, no. 11 (May 31, 2022): 4202. http://dx.doi.org/10.3390/s22114202.
Full textAbstract:
Event detection is an important task in the field of natural language processing, which aims to detect trigger words in a sentence and classify them into specific event types. Event detection tasks suffer from data sparsity and event instances imbalance problems in small-scale datasets. For this reason, the correlation information of event types can be used to alleviate the above problems. In this paper, we design a Hierarchical Attention Neural Network for Event Types (HANN-ET). Specifically, we select Long Short-Term Memory (LSTM) as the semantic encoder and utilize dynamic multi-pooling and the Graph Attention Network (GAT) to enrich the sentence feature. Meanwhile, we build several upper-level event type modules and employ a weighted attention aggregation mechanism to integrate these modules to obtain the correlation event type information. Each upper-level module is completed by a Neural Module Network (NMNs), event types within the same upper-level module can share information, and an attention aggregation mechanism can provide effective bias scores for the trigger word classifier. We conduct extensive experiments on the ACE2005 and the MAVEN datasets, and the results show that our approach outperforms previous state-of-the-art methods and achieves the competitive F1 scores of 78.9% on the ACE2005 dataset and 68.8% on the MAVEN dataset.
20
Tian, Qi, Kun Kuang, Furui Liu, and Baoxiang Wang. "Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 10 (June 26, 2023): 11672–80. http://dx.doi.org/10.1609/aaai.v37i10.26379.
Full textAbstract:
Offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets, which is an important step toward the deployment of multi-agent systems in real-world applications. However, in practice, each individual behavior policy that generates multi-agent joint trajectories usually has a different level of how well it performs. e.g., an agent is a random policy while other agents are medium policies. In the cooperative game with global reward, one agent learned by existing offline MARL often inherits this random policy, jeopardizing the utility of the entire team. In this paper, we investigate offline MARL with explicit consideration on the diversity of agent-wise trajectories and propose a novel framework called Shared Individual Trajectories (SIT) to address this problem. Specifically, an attention-based reward decomposition network assigns the credit to each agent through a differentiable key-value memory mechanism in an offline manner. These decomposed credits are then used to reconstruct the joint offline datasets into prioritized experience replay with individual trajectories, thereafter agents can share their good trajectories and conservatively train their policies with a graph attention network (GAT) based critic. We evaluate our method in both discrete control (i.e., StarCraft II and multi-agent particle environment) and continuous control (i.e., multi-agent mujoco). The results indicate that our method achieves significantly better results in complex and mixed offline multi-agent datasets, especially when the difference of data quality between individual trajectories is large.
21
Yang, Shuai, Yueqin Zhang, and Zehua Zhang. "Runoff Prediction Based on Dynamic Spatiotemporal Graph Neural Network." Water 15, no. 13 (July 5, 2023): 2463. http://dx.doi.org/10.3390/w15132463.
Full textAbstract:
Runoff prediction plays an important role in the construction of intelligent hydraulic engineering. Most of the existing deep learning runoff prediction models use recurrent neural networks for single-step prediction of a single time series, which mainly model the temporal features and ignore the river convergence process within a watershed. In order to improve the accuracy of runoff prediction, a dynamic spatiotemporal graph neural network model (DSTGNN) is proposed considering the interaction of hydrological stations. The sequences are first input to the spatiotemporal block to extract spatiotemporal features. The temporal features are captured by the long short-term memory network (LSTM) with the self-attention mechanism. Then, the upstream and downstream distance matrices are constructed based on the river network topology in the basin, the dynamic matrix is constructed based on the runoff sequence, and the spatial dependence is captured by combining the above two matrices through the diffusion process. After that, the residual sequences are input to the next layer by the decoupling block, and, finally, the prediction results are output after multi-layer stacking. Experiments are conducted on the historical runoff dataset in the Upper Delaware River Basin, and the MAE, MSE, MAPE, and NSE were the best compared with the baseline model for forecasting periods of 3 h, 6 h, and 9 h. The experimental results show that DSTGNN can better capture the spatiotemporal characteristics and has higher prediction accuracy.
22
Li, Youru, Zhenfeng Zhu, Deqiang Kong, Meixiang Xu, and Yao Zhao. "Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 1004–11. http://dx.doi.org/10.1609/aaai.v33i01.33011004.
Full textAbstract:
Bike-sharing systems, aiming at meeting the public’s need for ”last mile” transportation, are becoming popular in recent years. With an accurate demand prediction model, shared bikes, though with a limited amount, can be effectively utilized whenever and wherever there are travel demands. Despite that some deep learning methods, especially long shortterm memory neural networks (LSTMs), can improve the performance of traditional demand prediction methods only based on temporal representation, such improvement is limited due to a lack of mining complex spatial-temporal relations. To address this issue, we proposed a novel model named STG2Vec to learn the representation from heterogeneous spatial-temporal graph. Specifically, we developed an event-flow serializing method to encode the evolution of dynamic heterogeneous graph into a special language pattern such as word sequence in a corpus. Furthermore, a dynamic attention-based graph embedding model is introduced to obtain an importance-awareness vectorized representation of the event flow. Additionally, together with other multi-source information such as geographical position, historical transition patterns and weather, e.g., the representation learned by STG2Vec can be fed into the LSTMs for temporal modeling. Experimental results from Citi-Bike electronic usage records dataset in New York City have illustrated that the proposed model can achieve competitive prediction performance compared with its variants and other baseline models.
23
Liu, Lijuan, Mingxiao Wu, Rung-Ching Chen, Shunzhi Zhu, and Yan Wang. "A Hybrid Deep Learning Model for Multi-Station Classification and Passenger Flow Prediction." Applied Sciences 13, no. 5 (February 23, 2023): 2899. http://dx.doi.org/10.3390/app13052899.
Full textAbstract:
Multiple station passenger flow prediction is crucial but challenging for intelligent transportation systems. Recently, deep learning models have been widely applied in multi-station passenger flow prediction. However, flows at the same station in different periods, or different stations in the same period, always present different characteristics. These indicate that globally extracting spatio-temporal features for multi-station passenger flow prediction may only be powerful enough to achieve the excepted performance for some stations. Therefore, a novel two-step multi-station passenger flow prediction model is proposed. First, an unsupervised clustering method for station classification using pure passenger flow is proposed based on the Transformer encoder and K-Means. Two novel evaluation metrics are introduced to verify the effectiveness of the classification results. Then, based on the classification results, a passenger flow prediction model is proposed for every type of station. Residual network (ResNet) and graph convolution network (GCN) are applied for spatial feature extraction, and attention long short-term memory network (AttLSTM) is used for temporal feature extraction. Integrating results for every type of station creates a prediction model for all stations in the network. Experiments are conducted on two real-world ridership datasets. The proposed model performs better than unclassified results in multi-station passenger flow prediction.
24
Chen, Yun, Chengwei Liang, Dengcheng Liu, Qingren Niu, Xinke Miao, Guangyu Dong, Liguang Li, Shanbin Liao, Xiaoci Ni, and Xiaobo Huang. "Embedding-Graph-Neural-Network for Transient NOx Emissions Prediction." Energies 16, no. 1 (December 20, 2022): 3. http://dx.doi.org/10.3390/en16010003.
Full textAbstract:
Recently, Acritical Intelligent (AI) methodologies such as Long and Short-term Memory (LSTM) have been widely considered promising tools for engine performance calibration, especially for engine emission performance prediction and optimization, and Transformer is also gradually applied to sequence prediction. To carry out high-precision engine control and calibration, predicting long time step emission sequences is required. However, LSTM has the problem of gradient disappearance on too long input and output sequences, and Transformer cannot reflect the dynamic features of historic emission information which derives from cycle-by-cycle engine combustion events, which leads to low accuracy and weak algorithm adaptability due to the inherent limitations of the encoder-decoder structure. In this paper, considering the highly nonlinear relation between the multi-dimensional engine operating parameters the engine emission data outputs, an Embedding-Graph-Neural-Network (EGNN) model was developed combined with self-attention mechanism for the adaptive graph generation part of the GNN to capture the relationship between the sequences, improve the ability of predicting long time step sequences, and reduce the number of parameters to simplify network structure. Then, a sensor embedding method was adopted to make the model adapt to the data characteristics of different sensors, so as to reduce the impact of experimental hardware on prediction accuracy. The experimental results show that under the condition of long-time step forecasting, the prediction error of our model decreased by 31.04% on average compared with five other baseline models, which demonstrates the EGNN model can potentially be used in future engine calibration procedures.
25
Uddin, Md Azher, Joolekha Bibi Joolee, Young-Koo Lee, and Kyung-Ah Sohn. "A Novel Multi-Modal Network-Based Dynamic Scene Understanding." ACM Transactions on Multimedia Computing, Communications, and Applications 18, no. 1 (January 31, 2022): 1–19. http://dx.doi.org/10.1145/3462218.
Full textAbstract:
In recent years, dynamic scene understanding has gained attention from researchers because of its widespread applications. The main important factor in successfully understanding the dynamic scenes lies in jointly representing the appearance and motion features to obtain an informative description. Numerous methods have been introduced to solve dynamic scene recognition problem, nevertheless, a few concerns still need to be investigated. In this article, we introduce a novel multi-modal network for dynamic scene understanding from video data, which captures both spatial appearance and temporal dynamics effectively. Furthermore, two-level joint tuning layers are proposed to integrate the global and local spatial features as well as spatial and temporal stream deep features. In order to extract the temporal information, we present a novel dynamic descriptor, namely, Volume Symmetric Gradient Local Graph Structure ( VSGLGS ), which generates temporal feature maps similar to optical flow maps. However, this approach overcomes the issues of optical flow maps. Additionally, Volume Local Directional Transition Pattern ( VLDTP ) based handcrafted spatiotemporal feature descriptor is also introduced, which extracts the directional information through exploiting edge responses. Lastly, a stacked Bidirectional Long Short-Term Memory ( Bi-LSTM ) network along with a temporal mixed pooling scheme is designed to achieve the dynamic information without noise interference. The extensive experimental investigation proves that the proposed multi-modal network outperforms most of the state-of-the-art approaches for dynamic scene understanding.
26
Zhou, Hang, Junqing Yu, and Wei Yang. "Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 3769–77. http://dx.doi.org/10.1609/aaai.v37i3.25489.
Full textAbstract:
Learning discriminative features for effectively separating abnormal events from normality is crucial for weakly supervised video anomaly detection (WS-VAD) tasks. Existing approaches, both video and segment level label oriented, mainly focus on extracting representations for anomaly data while neglecting the implication of normal data. We observe that such a scheme is sub-optimal, i.e., for better distinguishing anomaly one needs to understand what is a normal state, and may yield a higher false alarm rate. To address this issue, we propose an Uncertainty Regulated Dual Memory Units (UR-DMU) model to learn both the representations of normal data and discriminative features of abnormal data. To be specific, inspired by the traditional global and local structure on graph convolutional networks, we introduce a Global and Local Multi-Head Self Attention (GL-MHSA) module for the Transformer network to obtain more expressive embeddings for capturing associations in videos. Then, we use two memory banks, one additional abnormal memory for tackling hard samples, to store and separate abnormal and normal prototypes and maximize the margins between the two representations. Finally, we propose an uncertainty learning scheme to learn the normal data latent space, that is robust to noise from camera switching, object changing, scene transforming, etc. Extensive experiments on XD-Violence and UCF-Crime datasets demonstrate that our method outperforms the state-of-the-art methods by a sizable margin.
27
Zhang, Suqi, Xinxin Wang, Wenfeng Wang, Ningjing Zhang, Yunhao Fang, and Jianxin Li. "Recommendation model based on intention decomposition and heterogeneous information fusion." Mathematical Biosciences and Engineering 20, no. 9 (2023): 16401–20. http://dx.doi.org/10.3934/mbe.2023732.
Full textAbstract:
<abstract> <p>In order to solve the problem of timeliness of user and item interaction intention and the noise caused by heterogeneous information fusion, a recommendation model based on intention decomposition and heterogeneous information fusion (IDHIF) is proposed. First, the intention of the recently interacting items and the users of the recently interacting candidate items is decomposed, and the short feature representation of users and items is mined through long-short term memory and attention mechanism. Then, based on the method of heterogeneous information fusion, the interactive features of users and items are mined on the user-item interaction graph, the social features of users are mined on the social graph, and the content features of the item are mined on the knowledge graph. Different feature vectors are projected into the same feature space through heterogeneous information fusion, and the long feature representation of users and items is obtained through splicing and multi-layer perceptron. The final representation of users and items is obtained by combining short feature representation and long feature representation. Compared with the baseline model, the AUC on the Last.FM and Movielens-1M datasets increased by 1.83 and 4.03 percentage points, respectively, the F1 increased by 1.28 and 1.58 percentage points, and the Recall@20 increased by 3.96 and 2.90 percentage points. The model proposed in this paper can better model the features of users and items, thus enriching the vector representation of users and items, and improving the recommendation efficiency.</p> </abstract>
28
Fang, Ziquan, Lu Pan, Lu Chen, Yuntao Du, and Yunjun Gao. "MDTP." Proceedings of the VLDB Endowment 14, no. 8 (April 2021): 1289–97. http://dx.doi.org/10.14778/3457390.3457394.
Full textAbstract:
Traffic prediction has drawn increasing attention for its ubiquitous real-life applications in traffic management, urban computing, public safety, and so on. Recently, the availability of massive trajectory data and the success of deep learning motivate a plethora of deep traffic prediction studies. However, the existing neural-network-based approaches tend to ignore the correlations between multiple types of moving objects located in the same spatio-temporal traffic area, which is suboptimal for traffic prediction analytics. In this paper, we propose a multi-source deep traffic prediction framework over spatio-temporal trajectory data, termed as MDTP. The framework includes two phases: spatio-temporal feature modeling and multi-source bridging. We present an enhanced graph convolutional network (GCN) model combined with long short-term memory network (LSTM) to capture the spatial dependencies and temporal dynamics of traffic in the feature modeling phase. In the multi-source bridging phase, we propose two methods, Sum and Concat, to connect the learned features from different trajectory data sources. Extensive experiments on two real-life datasets show that MDTP i) has superior efficiency, compared with classical time-series methods, machine learning methods, and state-of-the-art neural-network-based approaches; ii) offers a significant performance improvement over the single-source traffic prediction approach; and iii) performs traffic predictions in seconds even on tens of millions of trajectory data. we develop MDTP + , a user-friendly interactive system to demonstrate traffic prediction analysis.
29
Xie, Yu, Yuanqiao Zhang, Maoguo Gong, Zedong Tang, and Chao Han. "MGAT: Multi-view Graph Attention Networks." Neural Networks 132 (December 2020): 180–89. http://dx.doi.org/10.1016/j.neunet.2020.08.021.
Full text
30
Yao, Kaixuan, Jiye Liang, Jianqing Liang, Ming Li, and Feilong Cao. "Multi-view graph convolutional networks with attention mechanism." Artificial Intelligence 307 (June 2022): 103708. http://dx.doi.org/10.1016/j.artint.2022.103708.
Full text
31
Chen, Lei, Jie Cao, Youquan Wang, Weichao Liang, and Guixiang Zhu. "Multi-view Graph Attention Network for Travel Recommendation." Expert Systems with Applications 191 (April 2022): 116234. http://dx.doi.org/10.1016/j.eswa.2021.116234.
Full text
32
Zhang, Pengyu, Yong Zhang, Jingcheng Wang, and Baocai Yin. "MVMA-GCN: Multi-view multi-layer attention graph convolutional networks." Engineering Applications of Artificial Intelligence 126 (November 2023): 106717. http://dx.doi.org/10.1016/j.engappai.2023.106717.
Full text
33
Poologaindran, Anujan, Mike Hart, Tom Santarius, Stephen Price, Rohit Sinha, Mike Sughrue, Yaara Erez, Rafael Romero-Garcia, and John Suckling. "Longitudinal Connectome Analyses following Low-Grade Glioma Neurosurgery: Implications for Cognitive Rehabilitation." Neuro-Oncology 23, Supplement_4 (October 1, 2021): iv8. http://dx.doi.org/10.1093/neuonc/noab195.015.
Full textAbstract:
Abstract Aims Low-grade gliomas (LGG) slowly grow and infiltrate the brain's network architecture (the connectome). Unlike strokes that acutely damage the connectome, LGGs intricately remodel it, leading to varying deficits in executive function (i.e. attention, concentration, working memory). By longitudinally mapping the “mesoscale” architecture of the connectome, we may begin to systematically accelerate domain-general cognitive rehabilitation in LGG patients. In this study, we pursued the following aims: 1) track cognitive and connectome trajectories following LGG surgery, 2) determine optimal time period for cognitive rehabilitation, and 3) distinguish patients with perioperative predictors of long-term cognitive deficits (>1 year). Method With MRI and cognitive data from n=629 individuals across the lifespan, we first validated the structural, functional, and topological relevance of the multiple demand (MD) system for higher-order cognition. Next, in n=17 patients undergoing glioma surgery, we longitudinally acquired connectome and cognitive data: pre-surgery, post-surgery Day 1, Month 3, & 12. We assessed how glioma infiltration, surgery, and rehabilitation affected MD system trajectories at the single-subject level. Deploying transcriptomic and graph theoretical analyses, we tested if perioperative connectome modularity can accurately distinguish long-term cognitive trajectories. Results Controlling for age and sex, the MD system’s multi-scale architecture in health was positively associated with higher-order cognition (Catell’s fluid intelligence). Pre-operative glioma infiltration into the MD system was negatively associated with the number of long-term cognitive deficits (OCS-Bridge cognitive battery), suggesting its functional reorganisation. Mixed-effects modelling demonstrated the resilience of the MD system to infiltration and resection, while the early post-operative period was critical for effective neurorehabilitation. Graph analyses revealed perioperative modularity can distinguish patients with long-term cognitive deficits at one-year follow-up. Transcriptomic analyses of inter-module connector hubs revealed increased gene expression for mitochondrial metabolism and synaptic plasticity. Conclusion This is the first serial functional mapping of LGG patient trajectories for domain-general cognition. By assessing the mesoscale architecture, we demonstrate how connectomics can help overcome the intrinsic heterogeneity in LGG patients and predict long-term rehabilitation trajectories. We discuss how to identify neurobiologically-grounded personalised targets for 'interventional neurorehabilitation' following LGG surgery.
34
Tang, Chang, Xinwang Liu, Xinzhong Zhu, En Zhu, Zhigang Luo, Lizhe Wang, and Wen Gao. "CGD: Multi-View Clustering via Cross-View Graph Diffusion." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5924–31. http://dx.doi.org/10.1609/aaai.v34i04.6052.
Full textAbstract:
Graph based multi-view clustering has been paid great attention by exploring the neighborhood relationship among data points from multiple views. Though achieving great success in various applications, we observe that most of previous methods learn a consensus graph by building certain data representation models, which at least bears the following drawbacks. First, their clustering performance highly depends on the data representation capability of the model. Second, solving these resultant optimization models usually results in high computational complexity. Third, there are often some hyper-parameters in these models need to tune for obtaining the optimal results. In this work, we propose a general, effective and parameter-free method with convergence guarantee to learn a unified graph for multi-view data clustering via cross-view graph diffusion (CGD), which is the first attempt to employ diffusion process for multi-view clustering. The proposed CGD takes the traditional predefined graph matrices of different views as input, and learns an improved graph for each single view via an iterative cross diffusion process by 1) capturing the underlying manifold geometry structure of original data points, and 2) leveraging the complementary information among multiple graphs. The final unified graph used for clustering is obtained by averaging the improved view associated graphs. Extensive experiments on several benchmark datasets are conducted to demonstrate the effectiveness of the proposed method in terms of seven clustering evaluation metrics.
35
Zhu, Fujian, and Shaojie Dai. "Multi-view Attention Mechanism Learning for POI Recommendation." Journal of Physics: Conference Series 2258, no. 1 (April 1, 2022): 012041. http://dx.doi.org/10.1088/1742-6596/2258/1/012041.
Full textAbstract:
Abstract POI(point of interest) recommendation is a very necessary research field in both academic and commerce, however, predicting users’ potential points of interest is always faced with the problems of data sparsity and context semantics. Some studies have shown that graph embedding technology alleviates the problem of data sparsity to a certain extent. However, neither graph embedding techniques nor unsupervised learning models can adaptively learn the different effects of multiple relations between users and POIs, respectively. In view of this, we leverage the contextual information of users and POIs to build the multi-view affinity graphs(e.g. User-User, POI-POI and User-POI), and learn the latent representations of users and POIs based on the Graph Embedding technology and Attention mechanism, namely the GEA model. In particular, we first construct multi-view affinity graphs by using user’s social relationship, geographical distance and check-in behaviour, and embed them into a low dimensional shared space to learn the latent representation of users and POIs. Afterwards, in order to take advantage of the different effects of multiple relationships in the final recommendation task, we exploit the attention mechanism to obtain the fused latent representation and make recommendation according users’ potential preferences. Finally, we design a multi-task objective function for joint optimization to obtain more accurate recommendation results. Extensive experiments on Gowalla have verified the effectiveness of our model.
36
Zou, Yongqi, Wenjiang Feng, Juntao Zhang, and Jingfu Li. "Forecasting of Short-Term Load Using the MFF-SAM-GCN Model." Energies 15, no. 9 (April 25, 2022): 3140. http://dx.doi.org/10.3390/en15093140.
Full textAbstract:
Short-term load forecasting plays a significant role in the operation of power systems. Recently, deep learning has been generally employed in short-term load forecasting, primarily in the extraction of the characteristics of digital information in a single dimension without taking into account of the impact of external variables, particularly non-digital elements on load characteristics. In this paper, we propose a joint MFF-SAM-GCN to realize short-term load forecasting. First, we utilize a Bi-directional Long Short-Term Memory (Bi-LSTM) network and One-Dimensional Convolutional Neural Network (1D-CNN) in parallel connection to form a multi-feature fusion (MFF) framework, which can extract spatiotemporal correlation features of the load data. In addition, we introduce a Self-Attention Mechanism (SAM) to further enhance the feature extraction capability of the 1D-CNN network. Then with the deployment of a Graph Convolutional Network (GCN), the external non-digital features such as weather, strength, and direction of wind, etc., are extracted. Moreover, the generated weight matrices are incorporated into the load features to enhance feature recognition ability. Finally, we exploit Bayesian Optimization (BO) to find the optimal hyperparameters of the model to further improve the prediction accuracy. The simulation is taken from our proposed model and six benchmark schemes by using the bus load dataset of the Shandong Open Data Network, China. The results show that the RMSE of our proposed MFF-SAM-GCN model is 0.0284, while the SMAPE is 9.453%,the MBE is 0.025, and R-squared is 0.989, which is better than the selected three traditional machine learning methods and the three deep learning models.
37
Zou, Yongqi, Wenjiang Feng, Juntao Zhang, and Jingfu Li. "Forecasting of Short-Term Load Using the MFF-SAM-GCN Model." Energies 15, no. 9 (April 25, 2022): 3140. http://dx.doi.org/10.3390/en15093140.
Full textAbstract:
Short-term load forecasting plays a significant role in the operation of power systems. Recently, deep learning has been generally employed in short-term load forecasting, primarily in the extraction of the characteristics of digital information in a single dimension without taking into account of the impact of external variables, particularly non-digital elements on load characteristics. In this paper, we propose a joint MFF-SAM-GCN to realize short-term load forecasting. First, we utilize a Bi-directional Long Short-Term Memory (Bi-LSTM) network and One-Dimensional Convolutional Neural Network (1D-CNN) in parallel connection to form a multi-feature fusion (MFF) framework, which can extract spatiotemporal correlation features of the load data. In addition, we introduce a Self-Attention Mechanism (SAM) to further enhance the feature extraction capability of the 1D-CNN network. Then with the deployment of a Graph Convolutional Network (GCN), the external non-digital features such as weather, strength, and direction of wind, etc., are extracted. Moreover, the generated weight matrices are incorporated into the load features to enhance feature recognition ability. Finally, we exploit Bayesian Optimization (BO) to find the optimal hyperparameters of the model to further improve the prediction accuracy. The simulation is taken from our proposed model and six benchmark schemes by using the bus load dataset of the Shandong Open Data Network, China. The results show that the RMSE of our proposed MFF-SAM-GCN model is 0.0284, while the SMAPE is 9.453%,the MBE is 0.025, and R-squared is 0.989, which is better than the selected three traditional machine learning methods and the three deep learning models.
38
Wu, Fei, Changjiang Zheng, Chen Zhang, Junze Ma, and Kai Sun. "Multi-View Multi-Attention Graph Neural Network for Traffic Flow Forecasting." Applied Sciences 13, no. 2 (January 4, 2023): 711. http://dx.doi.org/10.3390/app13020711.
Full textAbstract:
The key to intelligent traffic control and guidance lies in accurate prediction of traffic flow. Since traffic flow data is nonlinear, complex, and dynamic, in order to overcome these issues, graph neural network techniques are employed to address these challenges. For this reason, we propose a deep-learning architecture called AMGC-AT and apply it to a real passenger flow dataset of the Hangzhou metro for evaluation. Based on a priori knowledge, we set up multi-view graphs to express the static feature similarity of each station in the metro network, such as geographic location and zone function, which are then input to the multi-graph neural network with the goal of extracting and aggregating features in order to realize the complex spatial dependence of each station’s passenger flow. Furthermore, based on periodic features of historical traffic flows, we categorize the flow data into three time patterns. Specifically, we propose two different self-attention mechanisms to fuse high-order spatiotemporal features of traffic flow. The final step is to integrate the two modules and obtain the output results using a gated convolution and a fully connected neural network. The experimental results show that the proposed model has better performance than eight other baseline models at 10 min, 15 min and 30 min time intervals.
39
Cui, Wanqiu, Junping Du, Dawei Wang, Feifei Kou, and Zhe Xue. "MVGAN: Multi-View Graph Attention Network for Social Event Detection." ACM Transactions on Intelligent Systems and Technology 12, no. 3 (July 19, 2021): 1–24. http://dx.doi.org/10.1145/3447270.
Full textAbstract:
Social networks are critical sources for event detection thanks to the characteristics of publicity and dissemination. Unfortunately, the randomness and semantic sparsity of the social network text bring significant challenges to the event detection task. In addition to text, time is another vital element in reflecting events since events are often followed for a while. Therefore, in this article, we propose a novel method named Multi-View Graph Attention Network (MVGAN) for event detection in social networks. It enriches event semantics through both neighbor aggregation and multi-view fusion in a heterogeneous social event graph. Specifically, we first construct a heterogeneous graph by adding the hashtag to associate the isolated short texts and describe events comprehensively. Then, we learn view-specific representations of events through graph convolutional networks from the perspectives of text semantics and time distribution, respectively. Finally, we design a hashtag-based multi-view graph attention mechanism to capture the intrinsic interaction across different views and integrate the feature representations to discover events. Extensive experiments on public benchmark datasets demonstrate that MVGAN performs favorably against many state-of-the-art social network event detection algorithms. It also proves that more meaningful signals can contribute to improving the event detection effect in social networks, such as published time and hashtags.
40
Huang, Zongmo, Yazhou Ren, Xiaorong Pu, Shudong Huang, Zenglin Xu, and Lifang He. "Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (June 26, 2023): 7936–43. http://dx.doi.org/10.1609/aaai.v37i7.25960.
Full textAbstract:
As one of the most important research topics in the unsupervised learning field, Multi-View Clustering (MVC) has been widely studied in the past decade and numerous MVC methods have been developed. Among these methods, the recently emerged Graph Neural Networks (GNN) shine a light on modeling both topological structure and node attributes in the form of graphs, to guide unified embedding learning and clustering. However, the effectiveness of existing GNN-based MVC methods is still limited due to the insufficient consideration in utilizing the self-supervised information and graph information, which can be reflected from the following two aspects: 1) most of these models merely use the self-supervised information to guide the feature learning and fail to realize that such information can be also applied in graph learning and sample weighting; 2) the usage of graph information is generally limited to the feature aggregation in these models, yet it also provides valuable evidence in detecting noisy samples. To this end, in this paper we propose Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering (SGDMC), which promotes the performance of GNN-based deep MVC models by making full use of the self-supervised information and graph information. Specifically, a novel attention-allocating approach that considers both the similarity of node attributes and the self-supervised information is developed to comprehensively evaluate the relevance among different nodes. Meanwhile, to alleviate the negative impact caused by noisy samples and the discrepancy of cluster structures, we further design a sample-weighting strategy based on the attention graph as well as the discrepancy between the global pseudo-labels and the local cluster assignment. Experimental results on multiple real-world datasets demonstrate the effectiveness of our method over existing approaches.
41
Wang, Li, Xin Wang, and Jiao Wang. "Rail Transit Prediction Based on Multi-View Graph Attention Networks." Journal of Advanced Transportation 2022 (July 6, 2022): 1–8. http://dx.doi.org/10.1155/2022/4672617.
Full textAbstract:
Traffic prediction is the cornerstone of intelligent transportation system. In recent years, graph neural network has become the mainstream traffic prediction method due to its excellent processing ability of unstructured data. However, the network relationship in the real world is more complex. Multiple nodes and various associations such as different types of stations and lines in rail transit always exist at the same time. In an end-to-end model, the training accuracy will suffer if the same weights are assigned to multiple views. Thus, this paper proposes a framework with multi-view and multi-layer attention, which aims to solve the problem of node prediction involving multiple relationships. Specifically, the proposed model maps multiple relationships into multiple views. A graph convolutional neural network of multiple views with multi-layer attention learns the optimal regression of nodes. Furthermore, the model uses an autoencoder module to alleviate the over-smoothing problem during the training phase. With the historical dataset of Beijing rail transit, the experiment proves that the prediction accuracy of the model is generally better than the baseline traffic prediction algorithms.
42
Ling, Yawen, Jianpeng Chen, Yazhou Ren, Xiaorong Pu, Jie Xu, Xiaofeng Zhu, and Lifang He. "Dual Label-Guided Graph Refinement for Multi-View Graph Clustering." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (June 26, 2023): 8791–98. http://dx.doi.org/10.1609/aaai.v37i7.26057.
Full textAbstract:
With the increase of multi-view graph data, multi-view graph clustering (MVGC) that can discover the hidden clusters without label supervision has attracted growing attention from researchers. Existing MVGC methods are often sensitive to the given graphs, especially influenced by the low quality graphs, i.e., they tend to be limited by the homophily assumption. However, the widespread real-world data hardly satisfy the homophily assumption. This gap limits the performance of existing MVGC methods on low homophilous graphs. To mitigate this limitation, our motivation is to extract high-level view-common information which is used to refine each view's graph, and reduce the influence of non-homophilous edges. To this end, we propose dual label-guided graph refinement for multi-view graph clustering (DuaLGR), to alleviate the vulnerability in facing low homophilous graphs. Specifically, DuaLGR consists of two modules named dual label-guided graph refinement module and graph encoder module. The first module is designed to extract the soft label from node features and graphs, and then learn a refinement matrix. In cooperation with the pseudo label from the second module, these graphs are refined and aggregated adaptively with different orders. Subsequently, a consensus graph can be generated in the guidance of the pseudo label. Finally, the graph encoder module encodes the consensus graph along with node features to produce the high-level pseudo label for iteratively clustering. The experimental results show the superior performance on coping with low homophilous graph data. The source code for DuaLGR is available at https://github.com/YwL-zhufeng/DuaLGR.
43
Lyu, Gengyu, Xiang Deng, Yanan Wu, and Songhe Feng. "Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7647–54. http://dx.doi.org/10.1609/aaai.v36i7.20731.
Full textAbstract:
In multi-view multi-label learning (MVML), each instance is described by several heterogeneous feature representations and associated with multiple valid labels simultaneously. Although diverse MVML methods have been proposed over the last decade, most previous studies focus on leveraging the shared subspace across different views to represent the multi-view consensus information, while it is still an open issue whether such shared subspace representation is necessary when formulating the desired MVML model. In this paper, we propose a DeepGCN based View-Specific MVML method (D-VSM) which can bypass seeking for the shared subspace representation, and instead directly encoding the feature representation of each individual view through the deep GCN to couple with the information derived from the other views. Specifically, we first construct all instances under different feature representations into the corresponding feature graphs respectively, and then integrate them into a unified graph by integrating the different feature representations of each instance. Afterwards, the graph attention mechanism is adopted to aggregate and update all nodes on the unified graph to form structural representation for each instance, where both intra-view correlations and inter-view alignments have been jointly encoded to discover the underlying semantic relations. Finally, we derive a label confidence score for each instance by averaging the label confidence of its different feature representations with the multi-label soft margin loss. Extensive experiments have demonstrated that our proposed method significantly outperforms state-of-the-art methods.
44
Zhang, Pei, Siwei Wang, Jingtao Hu, Zhen Cheng, Xifeng Guo, En Zhu, and Zhiping Cai. "Adaptive Weighted Graph Fusion Incomplete Multi-View Subspace Clustering." Sensors 20, no. 20 (October 10, 2020): 5755. http://dx.doi.org/10.3390/s20205755.
Full textAbstract:
With the enormous amount of multi-source data produced by various sensors and feature extraction approaches, multi-view clustering (MVC) has attracted developing research attention and is widely exploited in data analysis. Most of the existing multi-view clustering methods hold on the assumption that all of the views are complete. However, in many real scenarios, multi-view data are often incomplete for many reasons, e.g., hardware failure or incomplete data collection. In this paper, we propose an adaptive weighted graph fusion incomplete multi-view subspace clustering (AWGF-IMSC) method to solve the incomplete multi-view clustering problem. Firstly, to eliminate the noise existing in the original space, we transform complete original data into latent representations which contribute to better graph construction for each view. Then, we incorporate feature extraction and incomplete graph fusion into a unified framework, whereas two processes can negotiate with each other, serving for graph learning tasks. A sparse regularization is imposed on the complete graph to make it more robust to the view-inconsistency. Besides, the importance of different views is automatically learned, further guiding the construction of the complete graph. An effective iterative algorithm is proposed to solve the resulting optimization problem with convergence. Compared with the existing state-of-the-art methods, the experiment results on several real-world datasets demonstrate the effectiveness and advancement of our proposed method.
45
Shang, Chao, Qinqing Liu, Qianqian Tong, Jiangwen Sun, Minghu Song, and Jinbo Bi. "Multi-view spectral graph convolution with consistent edge attention for molecular modeling." Neurocomputing 445 (July 2021): 12–25. http://dx.doi.org/10.1016/j.neucom.2021.02.025.
Full text
46
Yu, Jinshi, Qi Duan, Haonan Huang, Shude He, and Tao Zou. "Effective Incomplete Multi-View Clustering via Low-Rank Graph Tensor Completion." Mathematics 11, no. 3 (January 28, 2023): 652. http://dx.doi.org/10.3390/math11030652.
Full textAbstract:
In the past decade, multi-view clustering has received a lot of attention due to the popularity of multi-view data. However, not all samples can be observed from every view due to some unavoidable factors, resulting in the incomplete multi-view clustering (IMC) problem. Up until now, most efforts for the IMC problem have been made on the learning of consensus representations or graphs, while many missing views are ignored, making it impossible to capture the information hidden in the missing view. To overcome this drawback, we first analyzed the low-rank relationship existing inside each graph and among all graphs, and then propose a novel method for the IMC problem via low-rank graph tensor completion. Specifically, we first stack all similarity graphs into a third-order graph tensor and then exploit the low-rank relationship from each mode using the matrix nuclear norm. In this way, the connection hidden between the missing and available instances can be recovered. The consensus representation can be learned from all completed graphs via multi-view spectral clustering. To obtain the optimal multi-view clustering result, incomplete graph recovery and consensus representation learning are integrated into a joint framework for optimization. Extensive experimental results on several incomplete multi-view datasets demonstrate that the proposed method can obtain a better clustering performance in comparison with state-of-the-art incomplete multi-view clustering methods.
47
Huang, Yanquan, Haoliang Yuan, and Loi Lei Lai. "Latent multi-view semi-supervised classification by using graph learning." International Journal of Wavelets, Multiresolution and Information Processing 18, no. 05 (June 20, 2020): 2050039. http://dx.doi.org/10.1142/s0219691320500393.
Full textAbstract:
Multi-view learning is a hot research direction in the field of machine learning and pattern recognition, which is attracting more and more attention recently. In the real world, the available data commonly include a small number of labeled samples and a large number of unlabeled samples. In this paper, we propose a latent multi-view semi-supervised classification method by using graph learning. This work recovers a latent intact representation to utilize the complementary information of the multi-view data. In addition, an adaptive graph learning technique is adopted to explore the local structure of this latent intact representation. To fully use this latent intact representation to discover the label information of the unlabeled data, we consider to unify the procedures of computing the latent intact representation and the labels of unlabeled data as a whole. An alternating optimization algorithm is designed to effectively solve the optimization of the proposed method. Extensive experimental results demonstrate the effectiveness of our proposed method.
48
Alothali, Eiman, Motamen Salih, Kadhim Hayawi, and Hany Alashwal. "Bot-MGAT: A Transfer Learning Model Based on a Multi-View Graph Attention Network to Detect Social Bots." Applied Sciences 12, no. 16 (August 13, 2022): 8117. http://dx.doi.org/10.3390/app12168117.
Full textAbstract:
Twitter, as a popular social network, has been targeted by different bot attacks. Detecting social bots is a challenging task, due to their evolving capacity to avoid detection. Extensive research efforts have proposed different techniques and approaches to solving this problem. Due to the scarcity of recently updated labeled data, the performance of detection systems degrades when exposed to a new dataset. Therefore, semi-supervised learning (SSL) techniques can improve performance, using both labeled and unlabeled examples. In this paper, we propose a framework based on the multi-view graph attention mechanism using a transfer learning (TL) approach, to predict social bots. We called the framework ‘Bot-MGAT’, which stands for bot multi-view graph attention network. The framework used both labeled and unlabeled data. We used profile features to reduce the overheads of the feature engineering. We executed our experiments on a recent benchmark dataset that included representative samples of social bots with graph structural information and profile features only. We applied cross-validation to avoid uncertainty in the model’s performance. Bot-MGAT was evaluated using graph SSL techniques: single graph attention networks (GAT), graph convolutional networks (GCN), and relational graph convolutional networks (RGCN). We compared Bot-MGAT to related work in the field of bot detection. The results of Bot-MGAT with TL outperformed, with an accuracy score of 97.8%, an F1 score of 0.9842, and an MCC score of 0.9481.
49
Zeng, Hui, Tianmeng Zhao, Ruting Cheng, Fuzhou Wang, and Jiwei Liu. "Hierarchical Graph Attention Based Multi-View Convolutional Neural Network for 3D Object Recognition." IEEE Access 9 (2021): 33323–35. http://dx.doi.org/10.1109/access.2021.3059853.
Full text
50
Zhu, Jiangqiang, Kai Li, Jinjia Peng, and Jing Qi. "Self-Supervised Graph Attention Collaborative Filtering for Recommendation." Electronics 12, no. 4 (February 5, 2023): 793. http://dx.doi.org/10.3390/electronics12040793.
Full textAbstract:
Due to the complementary nature of graph neural networks and structured data in recommendations, recommendation systems using graph neural network techniques have become mainstream. However, there are still problems, such as sparse supervised signals and interaction noise, in the recommendation task. Therefore, this paper proposes a self-supervised graph attention collaborative filtering for recommendation (SGACF). The correlation between adjacent nodes is deeply mined using a multi-head graph attention network to obtain accurate node representations. It is worth noting that self-supervised learning is brought in as an auxiliary task in the recommendation, where the supervision task is the main task. It assists model training for supervised tasks. A multi-view of a node is generated by the graph data-augmentation method. We maximize the consistency between its different views compared to the views of the same node and minimize the consistency between its different views compared to the views of other nodes. In this paper, the effectiveness of the method is illustrated by abundant experiments on three public datasets. The results show its significant improvement in the accuracy of the long-tail item recommendation and the robustness of the model.