Siga este link para ver outros tipos de publicações sobre o tema: Dynamic Graph Generation.
Artigos de revistas sobre o tema "Dynamic Graph Generation"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores artigos de revistas para estudos sobre o assunto "Dynamic Graph Generation".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja os artigos de revistas das mais diversas áreas científicas e compile uma bibliografia correta.
1
Fan, Shaohua, Shuyang Zhang, Xiao Wang e Chuan Shi. "Directed Acyclic Graph Structure Learning from Dynamic Graphs". Proceedings of the AAAI Conference on Artificial Intelligence 37, n.º 6 (26 de junho de 2023): 7512–21. http://dx.doi.org/10.1609/aaai.v37i6.25913.
Texto completo da fonteResumo:
Estimating the structure of directed acyclic graphs (DAGs) of features (variables) plays a vital role in revealing the latent data generation process and providing causal insights in various applications. Although there have been many studies on structure learning with various types of data, the structure learning on the dynamic graph has not been explored yet, and thus we study the learning problem of node feature generation mechanism on such ubiquitous dynamic graph data. In a dynamic graph, we propose to simultaneously estimate contemporaneous relationships and time-lagged interaction relationships between the node features. These two kinds of relationships form a DAG, which could effectively characterize the feature generation process in a concise way. To learn such a DAG, we cast the learning problem as a continuous score-based optimization problem, which consists of a differentiable score function to measure the validity of the learned DAGs and a smooth acyclicity constraint to ensure the acyclicity of the learned DAGs. These two components are translated into an unconstraint augmented Lagrangian objective which could be minimized by mature continuous optimization techniques. The resulting algorithm, named GraphNOTEARS, outperforms baselines on simulated data across a wide range of settings that may encounter in real-world applications. We also apply the proposed approach on two dynamic graphs constructed from the real-world Yelp dataset, demonstrating our method could learn the connections between node features, which conforms with the domain knowledge.
2
Ke, Qingchao, e Jian Lin. "Dynamic Generation of Knowledge Graph Supporting STEAM Learning Theme Design". Applied Sciences 12, n.º 21 (30 de outubro de 2022): 11001. http://dx.doi.org/10.3390/app122111001.
Texto completo da fonteResumo:
Instructional framework based on a knowledge graph makes up for the interdisciplinary theme design ability of teachers in a single discipline, to some extent, and provides a curriculum-oriented theme generation path for STEAM instructional design. This study proposed a dynamic completion model of a knowledge graph based on the subject semantic tensor decomposition. This model can be based on the tensor calculation of multi-disciplinary curriculum standard knowledge semantics to provide more reasonable STEAM project-based learning themes for teachers of those subjects. First, the STEAM multi-disciplinary knowledge semantic dataset was generated through the course’s standard text and open-source encyclopedia data. Next, based on the semantic tensor decomposition of specific STEAM topics, the dynamic generation of knowledge graphs was realized, providing interdisciplinary STEAM learning topic sequences for teachers of a single discipline. Finally, the application experiment of generating STEAM learning themes proved the effectiveness of our model.
3
Chen, Libin, Luyao Wang, Chengyi Zeng, Hongfu Liu e Jing Chen. "DHGEEP: A Dynamic Heterogeneous Graph-Embedding Method for Evolutionary Prediction". Mathematics 10, n.º 22 (9 de novembro de 2022): 4193. http://dx.doi.org/10.3390/math10224193.
Texto completo da fonteResumo:
Current graph-embedding methods mainly focus on static homogeneous graphs, where the entity type is the same and the topology is fixed. However, in real networks, such as academic networks and shopping networks, there are typically various types of nodes and temporal interactions. The dynamical and heterogeneous components of graphs in general contain abundant information. Currently, most studies on dynamic graphs do not sufficiently consider the heterogeneity of the network in question, and hence the semantic information of the interactions between heterogeneous nodes is missing in the graph embeddings. On the other hand, the overall size of the network tends to accumulate over time, and its growth rate can reflect the ability of the entire network to generate interactions of heterogeneous nodes; therefore, we developed a graph dynamics model to model the evolution of graph dynamics. Moreover, the temporal properties of nodes regularly affect the generation of temporal interaction events with which they are connected. Thus, we developed a node dynamics model to model the evolution of node connectivity. In this paper, we propose DHGEEP, a dynamic heterogeneous graph-embedding method based on the Hawkes process, to predict the evolution of dynamic heterogeneous networks. The model considers the generation of temporal events as an effect of historical events, introduces the Hawkes process to simulate this evolution, and then captures semantic and structural information based on the meta-paths of temporal heterogeneous nodes. Finally, the graph-level dynamics of the network and the node-level dynamics of each node are integrated into the DHGEEP framework. The embeddings of the nodes are automatically obtained by minimizing the value of the loss function. Experiments were conducted on three downstream tasks, static link prediction, temporal event prediction for homogeneous nodes, and temporal event prediction for heterogeneous nodes, on three datasets. Experimental results show that DHGEEP achieves excellent performance in these tasks. In the most significant task, temporal event prediction of heterogeneous nodes, the values of precision@2 and recall@2 can reach 30.23% and 10.48% on the AMiner dataset, and reach 4.56% and 1.61% on the DBLP dataset, so that our method is more accurate at predicting future temporal events than the baseline.
4
Yang, Yu, An Wang, Hua Wang, Wei-Ting Zhao e Dao-Qiang Sun. "On Subtrees of Fan Graphs, Wheel Graphs, and “Partitions” of Wheel Graphs under Dynamic Evolution". Mathematics 7, n.º 5 (24 de maio de 2019): 472. http://dx.doi.org/10.3390/math7050472.
Texto completo da fonteResumo:
The number of subtrees, or simply the subtree number, is one of the most studied counting-based graph invariants that has applications in many interdisciplinary fields such as phylogenetic reconstruction. Motivated from the study of graph surgeries on evolutionary dynamics, we consider the subtree problems of fan graphs, wheel graphs, and the class of graphs obtained from “partitioning” wheel graphs under dynamic evolution. The enumeration of these subtree numbers is done through the so-called subtree generation functions of graphs. With the enumerative result, we briefly explore the extremal problems in the corresponding class of graphs. Some interesting observations on the behavior of the subtree number are also presented.
5
Singh, Priyank Kumar, Sami Ur Rehman, Darshan J, Shobha G e Deepamala N. "Automated dynamic schema generation using knowledge graph". IAES International Journal of Artificial Intelligence (IJ-AI) 11, n.º 4 (1 de dezembro de 2022): 1261. http://dx.doi.org/10.11591/ijai.v11.i4.pp1261-1269.
Texto completo da fonteResumo:
<span>On the internet where the number of database developers is increasing with the availability of huge data to be stored and queried. Establishing relations between various schemas and helping the developers by filtering, prioritizing, and suggesting relevant schema is a requirement. Recommendation system plays an important role in searching through a large volume of dynamically generated schemas to provide database developers with personalized schemas and services. Although many methods are already available to solve problems using machine learning, they require more time and data to learn. These problems can be solved using knowledge graphs (KG). This paper investigates building knowledge graphs to recommend schemas. </span>
6
Kumari, Kabita, e Hashim Zahoor. "SmartGraphAI: Real Time Graph Generation with AI". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, n.º 11 (27 de novembro de 2024): 1–8. http://dx.doi.org/10.55041/ijsrem39110.
Texto completo da fonteResumo:
SmartGraphAI, an innovative web platform, is designed to revolutionize the way users generate graphs in real-time using AI and large language models (LLMs). By processing natural language queries, SmartGraphAI intelligently breaks down user requests into multiple sub-queries that retrieve relevant data from the internet. This data is then integrated into user-friendly visualizations through dynamic graphs that adapt to the user’s requirements. The platform leverages advanced LLM technology for query interpretation and utilizes web scraping APIs for real-time data extraction, ensuring that users receive up-to-date, accurate insights. The backend, built on FastAPI, manages the data flow seamlessly, while the frontend, developed with React, provides a smooth and intuitive interface for users to engage with. SmartGraphAI empowers professionals across industries to quickly transform complex data into meaningful visual insights, automating the entire process from query input to graph generation, and thus, enhancing decision-making and efficiency in data analysis. Keywords AI, Graph Generation, Real-Time, Large Language Models, Data Visualization, Web Scraping
7
Shen, Yanyan, Lei Chen, Jingzhi Fang, Xin Zhang, Shihong Gao e Hongbo Yin. "Efficient Training of Graph Neural Networks on Large Graphs". Proceedings of the VLDB Endowment 17, n.º 12 (agosto de 2024): 4237–40. http://dx.doi.org/10.14778/3685800.3685844.
Texto completo da fonteResumo:
Graph Neural Networks (GNNs) have gained significant popularity for learning representations of graph-structured data. Mainstream GNNs employ the message passing scheme that iteratively propagates information between connected nodes through edges. However, this scheme incurs high training costs, hindering the applicability of GNNs on large graphs. Recently, the database community has extensively researched effective solutions to facilitate efficient GNN training on massive graphs. In this tutorial, we provide a comprehensive overview of the GNN training process based on the graph data lifecycle, covering graph preprocessing, batch generation, data transfer, and model training stages. We discuss recent data management efforts aiming at accelerating individual stages or improving the overall training efficiency. Recognizing the distinct training issues associated with static and dynamic graphs, we first focus on efficient GNN training on static graphs, followed by an exploration of training GNNs on dynamic graphs. Finally, we suggest some potential research directions in this area. We believe this tutorial is valuable for researchers and practitioners to understand the bottleneck of GNN training and the advanced data management techniques to accelerate the training of different GNNs on massive graphs in diverse hardware settings.
8
Chen, I.-Ming, e Guilin Yang. "Automatic Model Generation for Modular Reconfigurable Robot Dynamics". Journal of Dynamic Systems, Measurement, and Control 120, n.º 3 (1 de setembro de 1998): 346–52. http://dx.doi.org/10.1115/1.2805408.
Texto completo da fonteResumo:
In control and simulation of a modular robot system, which consists of standardized and interconnected joint and link units, manual derivation of its dynamic model needs tremendous effort because these models change all the time as the robot geometry is altered after module reconfiguration. This paper presents a method to automate the generation of the closed-form equation of motion of a modular robot with arbitrary degrees-of-freedom and geometry. The robot geometry we consider here is branching type without loops. A graph technique, termed kinematic graphs and realized through assembly incidence matrices (AIM) is introduced to represent the module assembly sequence and robot geometry. The formulation of the dynamic model is started with recursive Newton-Euler algorithm. The generalized velocity, acceleration, and forces are expressed in terms of linear operations on se(3), the Lie algebra of the Euclidean group SE(3). Based on the equivalence relationship between the recursive formulation and the closed-form Lagrangian formulation, the accessibility matrix of the kinematic graph of the robot is used to assist the construction of the closed-form equation of motion of a modular robot. This automatic model generation technique can be applied to the control of rapidly reconfigurable robotic workcells and other automation equipment built around modular components that require accurate dynamic models.
9
Chen, Jin, Xiaofeng Ji e Xinxiao Wu. "Adaptive Image-to-Video Scene Graph Generation via Knowledge Reasoning and Adversarial Learning". Proceedings of the AAAI Conference on Artificial Intelligence 36, n.º 1 (28 de junho de 2022): 276–84. http://dx.doi.org/10.1609/aaai.v36i1.19903.
Texto completo da fonteResumo:
Scene graph in a video conveys a wealth of information about objects and their relationships in the scene, thus benefiting many downstream tasks such as video captioning and visual question answering. Existing methods of scene graph generation require large-scale training videos annotated with objects and relationships in each frame to learn a powerful model. However, such comprehensive annotation is time-consuming and labor-intensive. On the other hand, it is much easier and less cost to annotate images with scene graphs, so we investigate leveraging annotated images to facilitate training a scene graph generation model for unannotated videos, namely image-to-video scene graph generation. This task presents two challenges: 1) infer unseen dynamic relationships in videos from static relationships in images due to the absence of motion information in images; 2) adapt objects and static relationships from images to video frames due to the domain shift between them. To address the first challenge, we exploit external commonsense knowledge to infer the unseen dynamic relationship from the temporal evolution of static relationships. We tackle the second challenge by hierarchical adversarial learning to reduce the data distribution discrepancy between images and video frames. Extensive experiment results on two benchmark video datasets demonstrate the effectiveness of our method.
10
Maghawry, Noura, Samy Ghoniemy, Eman Shaaban e Karim Emara. "An Automatic Generation of Heterogeneous Knowledge Graph for Global Disease Support: A Demonstration of a Cancer Use Case". Big Data and Cognitive Computing 7, n.º 1 (24 de janeiro de 2023): 21. http://dx.doi.org/10.3390/bdcc7010021.
Texto completo da fonteResumo:
Semantic data integration provides the ability to interrelate and analyze information from multiple heterogeneous resources. With the growing complexity of medical ontologies and the big data generated from different resources, there is a need for integrating medical ontologies and finding relationships between distinct concepts from different ontologies where these concepts have logical medical relationships. Standardized Medical Ontologies are explicit specifications of shared conceptualization, which provide predefined medical vocabulary that serves as a stable conceptual interface to medical data sources. Intelligent Healthcare systems such as disease prediction systems require a reliable knowledge base that is based on Standardized medical ontologies. Knowledge graphs have emerged as a powerful dynamic representation of a knowledge base. In this paper, a framework is proposed for automatic knowledge graph generation integrating two medical standardized ontologies- Human Disease Ontology (DO), and Symptom Ontology (SYMP) using a medical online website and encyclopedia. The framework and methodologies adopted for automatically generating this knowledge graph fully integrated the two standardized ontologies. The graph is dynamic, scalable, easily reproducible, reliable, and practically efficient. A subgraph for cancer terms is also extracted and studied for modeling and representing cancer diseases, their symptoms, prevention, and risk factors.
11
Jung, Ga Young, e Incheol Kim. "Dynamic 3D Scene Graph Generation for Robotic Manipulation Tasks". Journal of Institute of Control, Robotics and Systems 27, n.º 12 (31 de dezembro de 2021): 953–63. http://dx.doi.org/10.5302/j.icros.2021.21.0140.
Texto completo da fonte
12
Karamti, Walid, e Adel Mahfoudhi. "States Graph Generation from dynamic Priority Time Petri Nets". International Journal of Open Problems in Computer Science and Mathematics 6, n.º 2 (junho de 2013): 85–100. http://dx.doi.org/10.12816/0006172.
Texto completo da fonte
13
Duan, Mingjiang, Tongya Zheng, Yang Gao, Gang Wang, Zunlei Feng e Xinyu Wang. "DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection". Proceedings of the AAAI Conference on Artificial Intelligence 38, n.º 10 (24 de março de 2024): 11820–28. http://dx.doi.org/10.1609/aaai.v38i10.29067.
Texto completo da fonteResumo:
Fraud detection has increasingly become a prominent research field due to the dramatically increased incidents of fraud. The complex connections involving thousands, or even millions of nodes, present challenges for fraud detection tasks. Many researchers have developed various graph-based methods to detect fraud from these intricate graphs. However, those methods neglect two distinct characteristics of the fraud graph: the non-additivity of certain attributes and the distinguishability of grouped messages from neighbor nodes. This paper introduces the Dynamic Grouping Aggregation Graph Neural Network (DGA-GNN) for fraud detection, which addresses these two characteristics by dynamically grouping attribute value ranges and neighbor nodes. In DGA-GNN, we initially propose the decision tree binning encoding to transform non-additive node attributes into bin vectors. This approach aligns well with the GNN’s aggregation operation and avoids nonsensical feature generation. Furthermore, we devise a feedback dynamic grouping strategy to classify graph nodes into two distinct groups and then employ a hierarchical aggregation. This method extracts more discriminative features for fraud detection tasks. Extensive experiments on five datasets suggest that our proposed method achieves a 3% ~ 16% improvement over existing SOTA methods. Code is available at https://github.com/AtwoodDuan/DGA-GNN.
14
Zhang, Jing, Guangli Wu, Xinlong Bi e Yulong Cui. "Video Summarization Generation Network Based on Dynamic Graph Contrastive Learning and Feature Fusion". Electronics 13, n.º 11 (23 de maio de 2024): 2039. http://dx.doi.org/10.3390/electronics13112039.
Texto completo da fonteResumo:
Video summarization aims to analyze the structure and content of videos and extract key segments to construct summarization that can accurately summarize the main content, allowing users to quickly access the core information without browsing the full video. However, existing methods have difficulties in capturing long-term dependencies when dealing with long videos. On the other hand, there is a large amount of noise in graph structures, which may lead to the influence of redundant information and is not conducive to the effective learning of video features. To solve the above problems, we propose a video summarization generation network based on dynamic graph contrastive learning and feature fusion, which mainly consists of three modules: feature extraction, video encoder, and feature fusion. Firstly, we compute the shot features and construct a dynamic graph by using the shot features as nodes of the graph and the similarity between the shot features as the weights of the edges. In the video encoder, we extract the temporal and structural features in the video using stacked L-G Blocks, where the L-G Block consists of a bidirectional long short-term memory network and a graph convolutional network. Then, the shallow-level features are obtained after processing by L-G Blocks. In order to remove the redundant information in the graph, graph contrastive learning is used to obtain the optimized deep-level features. Finally, to fully exploit the feature information of the video, a feature fusion gate using the gating mechanism is designed to fully fuse the shallow-level features with the deep-level features. Extensive experiments are conducted on two benchmark datasets, TVSum and SumMe, and the experimental results show that our proposed method outperforms most of the current state-of-the-art video summarization methods.
15
Choi, Gwang-Hyeok, Wonhee Lee e Tae-wan Kim. "Voyage optimization using dynamic programming with initial quadtree based route". Journal of Computational Design and Engineering 10, n.º 3 (29 de abril de 2023): 1185–203. http://dx.doi.org/10.1093/jcde/qwad055.
Texto completo da fonteResumo:
Abstract This research proposes an integrated voyage optimization algorithm that combines quadtree graph generation, visibility graph simplification, Dijkstra’s algorithm, and a 3D dynamic programming (3DDP) method. This approach enables the determination of a minimum distance initial reference route and the creation of a 2D navigational graph for efficient route optimization. We effectively store and process complex terrain information by transforming the GEBCO uniform grid into a quadtree structure. By utilizing a nearest neighbour search algorithm, edges are connected between adjacent ocean nodes, facilitating the generation of a quadtree graph. Applying Dijkstra’s algorithm to the quadtree graph, we derive the shortest initial route and construct a visibility graph based on the waypoints. This results in a simplified reference route with reduced search distance, allowing for more efficient navigation. For each waypoint along the reference route, a boundary is defined angled at 90 degrees to the left and right, based on the waypoint’s reference bearing. A line segment formed by the waypoint and both boundaries is defined as a navigational stage. A navigational graph is defined by connecting adjacent stages. Employing a 3DDP method on the navigational graph, and incorporating weather forecasting data, including wind, wave, and currents, we search for a route that minimizes fuel oil consumption with estimated time of arrival restrictions. Our approach is tested on several shipping routes, demonstrating a fuel consumption reduction compared to other voyage optimization routes. This integrated algorithm offers a potential solution for tackling complex voyage optimization problems in marine environments while considering various weather factors.
16
Kamejima, Kohji. "Stochastic Graph Minor Generation via Dynamic Reference to Geographics Annotation". Transactions of the Institute of Systems, Control and Information Engineers 25, n.º 12 (2012): 358–65. http://dx.doi.org/10.5687/iscie.25.358.
Texto completo da fonte
17
Kamejima, Kohji. "Probabilistic Graph Minor Generation with Dynamic Reference to Geographics Annotation". Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications 2012 (5 de maio de 2012): 192–97. http://dx.doi.org/10.5687/sss.2012.192.
Texto completo da fonte
18
Ding, Li, Tongqing Guo e Zhiliang Lu. "A Hybrid Method for Dynamic Mesh Generation Based on Radial Basis Functions and Delaunay Graph Mapping". Advances in Applied Mathematics and Mechanics 7, n.º 3 (28 de maio de 2015): 338–56. http://dx.doi.org/10.4208/aamm.2014.m614.
Texto completo da fonteResumo:
AbstractAiming at complex configuration and large deformation, an efficient hybrid method for dynamic mesh generation is presented in this paper, which is based on Radial Basis Functions (RBFs) and Delaunay graph mapping. Based on the computational mesh, a set of very coarse grid named as background grid is generated firstly, and then the computational mesh can be located at the background grid by Delaunay graph mapping technique. After that, the RBFs method is applied to deform the background grid by choosing partial mesh points on the boundary as the control points. Finally, Delaunay graph mapping method is used to relocate the computational mesh by employing area or volume weight coefficients. By applying different dynamic mesh methods to a moving NACA0012 airfoil, it can be found that the RBFs-Delaunay graph mapping hybrid method is as accurate as RBFs and is as efficient as Delaunay graph mapping technique. Numerical results show that the dynamic meshes for all test cases including one two-dimensional (2D) and two three-dimensional (3D) problems with different complexities, can be generated in an accurate and efficient manner by using the present hybrid method.
19
Fang, Zifan, Jiajia Wang, Fei Xiong e Xueyuan Xie. "Research on the dynamic characteristics of the acquisition mechanism of the oscillating flapping wing wave energy power generation device based on the bond graph". Journal of Physics: Conference Series 2125, n.º 1 (1 de novembro de 2021): 012050. http://dx.doi.org/10.1088/1742-6596/2125/1/012050.
Texto completo da fonteResumo:
Abstract Taking the acquisition mechanism of the oscillating flapping-wing wave energy power generation device as the research object, the design of the acquisition mechanism, the bond graph model of the acquisition mechanism and the dynamic characteristics are studied. According to the working principle of the acquisition mechanism of the oscillating flapping wing wave energy power generation device, the bond graph model and the state space equation of the acquisition mechanism are established. Based on the bond graph theory, the AMESim software is used for simulation analysis to verify the correctness of the bond graph model of the acquisition mechanism. The research results show that the designed oscillating flapping wing wave energy generation device acquisition mechanism responds quickly and stably, and the bond graph model basically matches the real system. The research process provides an effective reference for the development of the acquisition mechanism of the oscillating flapping wing wave energy power generation device.
20
Zhou, Junjie, Siyue Shuai, Lingyun Wang, Kaifeng Yu, Xiangjie Kong, Zuhua Xu e Zhijiang Shao. "Lane-Level Traffic Flow Prediction with Heterogeneous Data and Dynamic Graphs". Applied Sciences 12, n.º 11 (25 de maio de 2022): 5340. http://dx.doi.org/10.3390/app12115340.
Texto completo da fonteResumo:
With the continuous development of smart cities, intelligent transportation systems (ITSs) have ushered in many breakthroughs and upgrades. As a solid foundation for an ITS, traffic flow prediction effectively helps the city to better manage intricate traffic flow. However, existing traffic flow prediction methods such as temporal graph convolutional networks(T-GCNs) ignore the dissimilarities between lanes. Thus, they cannot provide more specific information regarding predictions such as dynamic changes in traffic flow direction and deeper lane relationships. With the upgrading of intersection sensors, more and more intersection lanes are equipped with intersection sensors to detect vehicle information all day long. These spatio-temporal data help researchers refine the focus of traffic prediction research down to the lane level. More accurate and detailed data mean that it is more difficult to mine the spatio-temporal correlations between data, and modeling heterogeneous data becomes more challenging. In order to deal with these problems, we propose a heterogeneous graph convolution model based on dynamic graph generation. The model consists of three components. The internal graph convolution network captures the real-time spatial dependency between lanes in terms of generated dynamic graphs. The external heterogeneous data fusion network comprehensively considers other parameters such as lane speed, lane occupancy, and weather conditions. The codec neural network utilizes a temporal attention mechanism to capture the deep temporal dependency. We test the performance of this model based on two real-world datasets, and extensive comparative experiments indicate that the proposed heterogeneous graph convolution model can improve the prediction accuracy.
21
Mabu, Shingo, Kotaro Hirasawa, Yuko Matsuya e Jinglu Hu. "Genetic Network Programming for Automatic Program Generation". Journal of Advanced Computational Intelligence and Intelligent Informatics 9, n.º 4 (20 de julho de 2005): 430–36. http://dx.doi.org/10.20965/jaciii.2005.p0430.
Texto completo da fonteResumo:
In this paper, a recently proposed Evolutionary Computation method called Genetic Network Programming (GNP) is applied to generate programs such as Boolean functions. GNP is an extension of Genetic Algorithm (GA) and Genetic Programming (GP). It has a directed graph structure as gene and can search for solutions effectively. GNP has been mainly applied to dynamic problems and has shown better performances compared to GP. However, its application to static problems has not yet been studied well. Thus in this paper, GNP is applied to generate programs as its extension to solving static problems. In order to apply GNP to generating static problems, we introduced a new element, memory. In the proposed method, a GNP individual consists of a directed graph and a memory, while one in conventional GNP consists only of a directed graph. In the simulations, GNP succeeded in solving Even-n-Parity problem and Mirror Symmetry problem.
22
Qi, Chao, Jianqin Yin, Zhicheng Zhang e Jin Tang. "Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning". Tsinghua Science and Technology 29, n.º 1 (fevereiro de 2024): 232–43. http://dx.doi.org/10.26599/tst.2023.9010002.
Texto completo da fonte
23
Lin, Xin, Chong Shi, Yibing Zhan, Zuopeng Yang, Yaqi Wu e Dacheng Tao. "TD²-Net: Toward Denoising and Debiasing for Video Scene Graph Generation". Proceedings of the AAAI Conference on Artificial Intelligence 38, n.º 4 (24 de março de 2024): 3495–503. http://dx.doi.org/10.1609/aaai.v38i4.28137.
Texto completo da fonteResumo:
Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might contain occluded and blurred objects. 2) Label bias, primarily due to the high imbalance between a few positive relationship samples and numerous negative ones. Additionally, the distribution of relationships exhibits a long-tailed pattern. To address the above problems, in this paper, we introduce a network named TD2-Net that aims at denoising and debiasing for dynamic SGG. Specifically, we first propose a denoising spatio-temporal transformer module that enhances object representation with robust contextual information. This is achieved by designing a differentiable Top-K object selector that utilizes the gumbel-softmax sampling strategy to select the relevant neighborhood for each object. Second, we introduce an asymmetrical reweighting loss to relieve the issue of label bias. This loss function integrates asymmetry focusing factors and the volume of samples to adjust the weights assigned to individual samples. Systematic experimental results demonstrate the superiority of our proposed TD2-Net over existing state-of-the-art approaches on Action Genome databases. In more detail, TD2-Net outperforms the second-best competitors by 12.7% on mean-Recall@10 for predicate classification.
24
Liu, Huimin, Qiu Yang, Xuexi Yang, Jianbo Tang, Min Deng e Rong Gui. "Coupling Hyperbolic GCN with Graph Generation for Spatial Community Detection and Dynamic Evolution Analysis". ISPRS International Journal of Geo-Information 13, n.º 7 (10 de julho de 2024): 248. http://dx.doi.org/10.3390/ijgi13070248.
Texto completo da fonteResumo:
Spatial community detection is a method that divides geographic spaces into several sub-regions based on spatial interactions, reflecting the regional spatial structure against the background of human mobility. In recent years, spatial community detection has attracted extensive research in the field of geographic information science. However, mining the community structures and their evolutionary patterns from spatial interaction data remains challenging. Most existing methods for spatial community detection rely on representing spatial interaction networks in Euclidean space, which results in significant distortion when modeling spatial interaction networks; since spatial community detection has no ground truth, this results in the detection and evaluation of communities being difficult. Furthermore, most methods usually ignore the dynamics of these spatial interaction networks, resulting in the dynamic evolution of spatial communities not being discussed in depth. Therefore, this study proposes a framework for community detection and evolutionary analysis for spatial interaction networks. Specifically, we construct a spatial interaction network based on network science theory, where geographic units serve as nodes and interaction relationships serve as edges. In order to fully learn the structural features of the spatial interaction network, we introduce a hyperbolic graph convolution module in the community detection phase to learn the spatial and non-spatial attributes of the spatial interaction network, obtain vector representations of the nodes, and optimize them based on a graph generation model to achieve the final community detection results. Considering the dynamics of spatial interactions, we analyze the evolution of the spatial community over time. Finally, using taxi trajectory data as an example, we conduct relevant experiments within the fifth ring road of Beijing. The empirical results validate the community detection capabilities of the proposed method, which can effectively describe the dynamic spatial structure of cities based on human mobility and provide an effective analytical method for urban spatial planning.
25
Agrawal, Smita, e Atul Patel. "Clustering Algorithm for Community Detection in Complex Network: A Comprehensive Review". Recent Advances in Computer Science and Communications 13, n.º 4 (19 de outubro de 2020): 542–49. http://dx.doi.org/10.2174/2213275912666190710183635.
Texto completo da fonteResumo:
Many real-world social networks exist in the form of a complex network, which includes very large scale networks with structured or unstructured data and a set of graphs. This complex network is available in the form of brain graph, protein structure, food web, transportation system, World Wide Web, and these networks are sparsely connected, and most of the subgraphs are densely connected. Due to the scaling of large scale graphs, efficient way for graph generation, complexity, the dynamic nature of graphs, and community detection are challenging tasks. From large scale graph to find the densely connected subgraph from the complex network, various community detection algorithms using clustering techniques are discussed here. In this paper, we discussed the taxonomy of various community detection algorithms like Structural Clustering Algorithm for Networks (SCAN), Structural-Attribute based Cluster (SA-cluster), Community Detection based on Hierarchical Clustering (CDHC), etc. In this comprehensive review, we provide a classification of community detection algorithm based on their approach, dataset used for the existing algorithm for experimental study and measure to evaluate them. In the end, insights into the future scope and research opportunities for community detection are discussed.
26
He, Yufeng, Barbara Hofer, Yehua Sheng e Yi Huang. "Dynamic Representations of Spatial Events – The Example of a Typhoon". AGILE: GIScience Series 2 (4 de junho de 2021): 1–7. http://dx.doi.org/10.5194/agile-giss-2-30-2021.
Texto completo da fonteResumo:
Abstract. The Geographic scene is a conceptual model that provides a holistic representation of the environment. This model has been developed in order to overcome limitations of geographic information systems (GIS) concerning interactions between features and the representation of dynamics. This contribution translates the theoretical model into an implementation of a dynamic data model in the graph database Neo4j and applies it to GIS data representing the dynamic information of a typhoon. The specific focus of the contribution is on choices made in the process of generation of the implementation of the example and the potential queries it supports.
27
Zhu, Wenhao, Yujun Xie, Qun Huang, Zehua Zheng, Xiaozhao Fang, Yonghui Huang e Weijun Sun. "Graph Transformer Collaborative Filtering Method for Multi-Behavior Recommendations". Mathematics 10, n.º 16 (16 de agosto de 2022): 2956. http://dx.doi.org/10.3390/math10162956.
Texto completo da fonteResumo:
Graph convolutional networks are widely used in recommendation tasks owing to their ability to learn user and item embeddings using collaborative signals from high-order neighborhoods. Most of the graph convolutional recommendation tasks in existing studies have specialized in modeling a single type of user–item interaction preference. Meanwhile, graph-convolution-network-based recommendation models are prone to over-smoothing problems when stacking increased numbers of layers. Therefore, in this study we propose a multi-behavior recommendation method based on graph transformer collaborative filtering. This method utilizes an unsupervised subgraph generation model that divides users with similar preferences and their interaction items into subgraphs. Furthermore, it fuses multi-headed attention layers with temporal coding strategies based on the user–item interaction graphs in the subgraphs such that the learned embeddings can reflect multiple user–item relationships and the potential for dynamic interactions. Finally, multi-behavior recommendation is performed by uniting multi-layer embedding representations. The experimental results on two real-world datasets show that the proposed method performs better than previously developed systems.
28
Du, Yuanqi, Xiaojie Guo, Hengning Cao, Yanfang Ye e Liang Zhao. "Disentangled Spatiotemporal Graph Generative Models". Proceedings of the AAAI Conference on Artificial Intelligence 36, n.º 6 (28 de junho de 2022): 6541–49. http://dx.doi.org/10.1609/aaai.v36i6.20607.
Texto completo da fonteResumo:
Spatiotemporal graph represents a crucial data structure where the nodes and edges are embedded in a geometric space and their attribute values can evolve dynamically over time. Nowadays, spatiotemporal graph data is becoming increasingly popular and important, ranging from microscale (e.g. protein folding), to middle-scale (e.g. dynamic functional connectivity), to macro-scale (e.g. human mobility network). Although disentangling and understanding the correlations among spatial, temporal, and graph aspects have been a long-standing key topic in network science, they typically rely on network processes hypothesized by human knowledge. They usually fit well towards the properties that the predefined principles are tailored for, but usually cannot do well for the others, especially for many key domains where the human has yet very limited knowledge such as protein folding and biological neuronal networks. In this paper, we aim at pushing forward the modeling and understanding of spatiotemporal graphs via new disentangled deep generative models. Specifically, a new Bayesian model is proposed that factorizes spatiotemporal graphs into spatial, temporal, and graph factors as well as the factors that explain the interplay among them. A variational objective function and new mutual information thresholding algorithms driven by information bottleneck theory have been proposed to maximize the disentanglement among the factors with theoretical guarantees. Qualitative and quantitative experiments on both synthetic and real-world datasets demonstrate the superiority of the proposed model over the state-of-the-arts by up to 69.2% for graph generation and 41.5% for interpretability.
29
Li, Shufei, Pai Zheng, Zuoxu Wang, Junming Fan e Lihui Wang. "Dynamic Scene Graph for Mutual-Cognition Generation in Proactive Human-Robot Collaboration". Procedia CIRP 107 (2022): 943–48. http://dx.doi.org/10.1016/j.procir.2022.05.089.
Texto completo da fonte
30
Fischer, Frank, e Christoph Helmberg. "Dynamic graph generation for the shortest path problem in time expanded networks". Mathematical Programming 143, n.º 1-2 (30 de outubro de 2012): 257–97. http://dx.doi.org/10.1007/s10107-012-0610-3.
Texto completo da fonte
31
Krishnaveni P e Balasundaram S R. "Summarizing Learning Materials Using Graph Based Multi-Document Summarization". International Journal of Web-Based Learning and Teaching Technologies 16, n.º 5 (setembro de 2021): 39–57. http://dx.doi.org/10.4018/ijwltt.20210901.oa3.
Texto completo da fonteResumo:
The learners and teachers of the teaching-learning process highly depend on online learning systems such as E-learning, which contains huge volumes of electronic contents related to a course. The multi-document summarization (MDS) is useful for summarizing such electronic contents. This article applies the task of MDS in an E-learning context. The objective of this article is threefold: 1) design a generic graph based multi-document summarizer DSGA (Dynamic Summary Generation Algorithm) to produce a variable length (dynamic) summary of academic text based learning materials based on a learner's request; 2) analyze the summary generation process; 3) perform content-based and task-based evaluations on the generated summary. The experimental results show that the DSGA summarizer performs better than the graph-based summarizers LexRank (LR) and Aggregate Similarity (AS). From the task-based evaluation, it is observed that the generated summary helps the learners to understand and comprehend the materials easily.
32
Setyawan, Moh Arsyad Mubarak, Fajar Pradana e Bayu Priyambadha. "Pengembangan sistem otomatisasi pembangkitan kasus uji dengan algoritma genetika dan test case generation method". teknologi 10, n.º 1 (4 de abril de 2020): 1. http://dx.doi.org/10.26594/teknologi.v10i1.1912.
Texto completo da fonteResumo:
Pengujian perangkat lunak merupakan salah satu bagian penting dari pembuatan perangkat lunak. Pada pengujian perangkat lunak terdapat pengujian unit. Pengujian unit merupakan proses pengujian komponen yang berfokus untuk memverifikasi unit terkecil pada perancangan perangkat lunak. Pada tahap pengujian unit terdapat proses pembangkitan kasus uji. Selama ini, pembangkitan kasus uji dari suatu kode program dilakukan secara manual se-hingga membutuhkan waktu yang lama. Hal ini dikarenakan banyaknya kemungkinan jalur pada kode sumber yang akan diuji. Dalam penelitian ini dibangun suatu sistem otomatis untuk membangkitkan kasus uji. Alur kerja sistem dimulai dari analisa kode sumber dengan Spoon Library, selanjutnya dibentuk CFG (Control Flow Graph) dan DDG (Dynamic Directed Graph). Dari DDG tersebut akan dibangkitkan jalur layak yang terdapat pada DDG, dengan menggunakan algoritma genetika diharapkan dapat mengoptimalkan penentuan jalur independen. Dari masing-masing jalur independen akan dibangkitkan kasus ujinya dengan metode test case generation. Pengujian akurasi sistem pada sistem otomatisasi pembangkit kasus uji dengan jumlah populasi 5, 10 dan 15 serta jumlah maksimum generasi 50, 100, 200 dan 250 dihasilkan jumlah populasi paling optimal yaitu 10 dan maksimum generasi optimal yaitu 200 dengan akurasi 93,33%. Pada jumlah populasi dan maksimum generasi sesudahnya tidak terjadi peningkatan akurasi yang signifikan. Tiap peningkatan jumlah populasi dan maksimum generasi dapat meningkatkan akurasi sistem. Software testing is one of the most important part of making software. On the software testing there are unit testing. Unit Testing is a process for verifying component, focusing on the smallest unit of software design. In the unit testing phase contained test case generation process. During this time, the generation of test cases of a program code is done manually. In this study, constructed an automated system to generate test cases. The workflow system starts from the analysis of the source code with the library spoon and then create CFG (Control Flow Graph) and DDG (Dynamic Directed graph). From the DDG will be raised feasible path using a genetic algorithm. Furthermore, from fea-sible path sought independenth path which is a path base d on the level of uniqueness of the path to the other path. From each independenth path raised the test case with a test case generation method. Testing accuracy of the system on the automation system generating test cases with populations of 5,10 and 15 as well as the maximum number of generations 50, 100, 200 and 250 produced the most optimal population number is 15 and the most optimal maximum generation is 200 with accuracy 93.33%. Each increase in the number of population and maximum generation can improve the accuracy of the system. Level accuracy with population number over 10 and maximum generation over 200 has no increace accuracy significant.
33
Wei, Zhuangkun, Liang Wang, Schyler Chengyao Sun, Bin Li e Weisi Guo. "Graph Layer Security: Encrypting Information via Common Networked Physics". Sensors 22, n.º 10 (23 de maio de 2022): 3951. http://dx.doi.org/10.3390/s22103951.
Texto completo da fonteResumo:
The proliferation of low-cost Internet of Things (IoT) devices has led to a race between wireless security and channel attacks. Traditional cryptography requires high computational power and is not suitable for low-power IoT scenarios. Whilst recently developed physical layer security (PLS) can exploit common wireless channel state information (CSI), its sensitivity to channel estimation makes them vulnerable to attacks. In this work, we exploit an alternative common physics shared between IoT transceivers: the monitored channel-irrelevant physical networked dynamics (e.g., water/oil/gas/electrical signal-flows). Leveraging this, we propose, for the first time, graph layer security (GLS), by exploiting the dependency in physical dynamics among network nodes for information encryption and decryption. A graph Fourier transform (GFT) operator is used to characterise such dependency into a graph-bandlimited subspace, which allows the generation of channel-irrelevant cipher keys by maximising the secrecy rate. We evaluate our GLS against designed active and passive attackers, using IEEE 39-Bus system. Results demonstrate that GLS is not reliant on wireless CSI, and can combat attackers that have partial networked dynamic knowledge (realistic access to full dynamic and critical nodes remains challenging). We believe this novel GLS has widespread applicability in secure health monitoring and for digital twins in adversarial radio environments.
34
Andrus, Berkeley R., Yeganeh Nasiri, Shilong Cui, Benjamin Cullen e Nancy Fulda. "Enhanced Story Comprehension for Large Language Models through Dynamic Document-Based Knowledge Graphs". Proceedings of the AAAI Conference on Artificial Intelligence 36, n.º 10 (28 de junho de 2022): 10436–44. http://dx.doi.org/10.1609/aaai.v36i10.21286.
Texto completo da fonteResumo:
Large transformer-based language models have achieved incredible success at various tasks which require narrative comprehension, including story completion, answering questions about stories, and generating stories ex nihilo. However, due to the limitations of finite context windows, these language models struggle to produce or understand stories longer than several thousand tokens. In order to mitigate the document length limitations that come with finite context windows, we introduce a novel architecture that augments story processing with an external dynamic knowledge graph. In contrast to static commonsense knowledge graphs which hold information about the real world, these dynamic knowledge graphs reflect facts extracted from the story being processed. Our architecture uses these knowledge graphs to create information-rich prompts which better facilitate story comprehension than prompts composed only of story text. We apply our architecture to the tasks of question answering and story completion. To complement this line of research, we introduce two long-form question answering tasks, LF-SQuAD and LF-QUOREF, in which the document length exceeds the size of the language model's context window, and introduce a story completion evaluation method that bypasses the stochastic nature of language model generation. We demonstrate broad improvement over typical prompt formulation methods for both question answering and story completion using GPT-2, GPT-3 and XLNet.
35
Herpers, R., e G. Sommer. "Discrimination of Facial Regions Based on Dynamic Grids of Point Representations". International Journal of Pattern Recognition and Artificial Intelligence 12, n.º 04 (junho de 1998): 381–405. http://dx.doi.org/10.1142/s0218001498000257.
Texto completo da fonteResumo:
The application of an elastic graph-matching approach to discriminate facial image regions is presented. In contrast to the dynamic link architecture introduced by the Malsburg group, our application is not an identification task but a classification task. Therefore, our approach differs in several important aspects: (1) the choice of the filter set, (2) the selection of the positions of the nodes of the graph to represent the characteristic image information, (3) the generation of a representative reference pattern needed for the calculation of the classifications, and (4) a new two-step graph-matching approach based on the simulated annealing technique. The approach was tested on facial regions taking the eye region as an example target. A classification performance for the verification of eye regions of more than 93% was achieved.
36
Lee, Hyeonbyeong, Bokyoung Shin, Dojin Choi, Jongtae Lim, Kyoungsoo Bok e Jaesoo Yoo. "Graph Stream Compression Scheme Based on Pattern Dictionary Using Provenance". Applied Sciences 14, n.º 11 (25 de maio de 2024): 4553. http://dx.doi.org/10.3390/app14114553.
Texto completo da fonteResumo:
With recent advancements in network technology and the increasing popularity of the internet, the use of social network services and Internet of Things devices has flourished, leading to a continuous generation of large volumes of graph stream data, where changes, such as additions or deletions of vertices and edges, occur over time. Additionally, owing to the need for the efficient use of storage space and security requirements, graph stream data compression has become essential in various applications. Even though various studies on graph compression methods have been conducted, most of them do not fully reflect the dynamic characteristics of graph streams and the complexity of large graphs. In this paper, we propose a compression scheme using provenance data to efficiently process and analyze large graph stream data. It obtains provenance data by analyzing graph stream data and builds a pattern dictionary based on this to perform dictionary-based compression. By improving the existing dictionary-based graph compression methods, it enables more efficient dictionary management through tracking pattern changes and evaluating their importance using provenance. Furthermore, it considers the relationships among sub-patterns using an FP-tree and performs pattern dictionary management that updates pattern scores based on time. Our experiments show that the proposed scheme outperforms existing graph compression methods in key performance metrics, such as compression rate and processing time.
37
Hu, Xiao, Zezhen Zhang, Zhiyu Fan, Jinduo Yang, Jiaquan Yang, Shaolun Li e Xuehao He. "GCN-Transformer-Based Spatio-Temporal Load Forecasting for EV Battery Swapping Stations under Differential Couplings". Electronics 13, n.º 17 (27 de agosto de 2024): 3401. http://dx.doi.org/10.3390/electronics13173401.
Texto completo da fonteResumo:
To address the challenge of power absorption in grids with high renewable energy integration, electric vehicle battery swapping stations (EVBSSs) serve as critically important flexible resources. Current research on load forecasting for EVBSSs primarily employs Transformer models, which have increasingly shown a lack of adaptability to the rapid growth in scale and complexity. This paper proposes a novel data-driven forecasting model that combines the geographical feature extraction capability of graph convolutional networks (GCNs) with the multitask learning capability of Transformers. The GCN-Transformer model first leverages Spearman’s rank correlation to create a multinode feature set encompassing date, weather, and historical load data. It then employs data-adaptive graph generation for dynamic spatio-temporal graph construction and graph convolutional layers for spatial aggregation tailored to each node. Unique swapping patterns are identified through node-adaptive parameter learning, while the temporal dynamics of multidimensional features are managed by the Transformer’s components. Numerical results demonstrate enhanced accuracy and efficiency in load forecasting for multiple and widely distributed EVBSSs.
38
Jia, Zhiwei, Honghui Li, Jiahe Yan, Jing Sun, Chengshan Han e Jingqi Qu. "Dynamic Graph Convolution-Based Spatio-Temporal Feature Network for Urban Water Demand Forecasting". Applied Sciences 13, n.º 18 (5 de setembro de 2023): 10014. http://dx.doi.org/10.3390/app131810014.
Texto completo da fonteResumo:
Urban water demand forecasting is the key component of smart water, which plays an important role in building a smart city. Although various methods have been proposed to improve forecast accuracy, most of these methods lack the ability to model spatio-temporal correlations. When dealing with the rich water demand monitoring data currently, it is difficult to achieve the desired prediction results. To address this issue from the perspective of improving the ability to extract temporal and spatial features, we propose a dynamic graph convolution-based spatio-temporal feature network (DG-STFN) model. Our model contains two major components, one is the dynamic graph generation module, which builds the dynamic graph structure based on the attention mechanism, and the other is the spatio-temporal feature block, which extracts the spatial and temporal features through graph convolution and conventional convolution. Based on the Shenzhen urban water supply dataset, five models SARIMAX, LSTM, STGCN, DCRNN, and ASTGCN are used to compare with DG-STFN proposed. The results show that DG-STFN outperforms the other models.
39
Hansknecht, Christoph, Imke Joormann e Sebastian Stiller. "Dynamic Shortest Paths Methods for the Time-Dependent TSP". Algorithms 14, n.º 1 (12 de janeiro de 2021): 21. http://dx.doi.org/10.3390/a14010021.
Texto completo da fonteResumo:
The time-dependent traveling salesman problem (TDTSP) asks for a shortest Hamiltonian tour in a directed graph where (asymmetric) arc-costs depend on the time the arc is entered. With traffic data abundantly available, methods to optimize routes with respect to time-dependent travel times are widely desired. This holds in particular for the traveling salesman problem, which is a corner stone of logistic planning. In this paper, we devise column-generation-based IP methods to solve the TDTSP in full generality, both for arc- and path-based formulations. The algorithmic key is a time-dependent shortest path problem, which arises from the pricing problem of the column generation and is of independent interest—namely, to find paths in a time-expanded graph that are acyclic in the underlying (non-expanded) graph. As this problem is computationally too costly, we price over the set of paths that contain no cycles of length k. In addition, we devise—tailored for the TDTSP—several families of valid inequalities, primal heuristics, a propagation method, and a branching rule. Combining these with the time-dependent shortest path pricing we provide—to our knowledge—the first elaborate method to solve the TDTSP in general and with fully general time-dependence. We also provide for results on complexity and approximability of the TDTSP. In computational experiments on randomly generated instances, we are able to solve the large majority of small instances (20 nodes) to optimality, while closing about two thirds of the remaining gap of the large instances (40 nodes) after one hour of computation.
40
Zeng, Yan, Wei Wang, Yong Ding, Jilin Zhang, Yongjian Ren e Guangzheng Yi. "Adaptive Distributed Parallel Training Method for a Deep Learning Model Based on Dynamic Critical Paths of DAG". Mathematics 10, n.º 24 (16 de dezembro de 2022): 4788. http://dx.doi.org/10.3390/math10244788.
Texto completo da fonteResumo:
AI provides a new method for massive simulated data calculations in molecular dynamics, materials, and other scientific computing fields. However, the complex structures and large-scale parameters of neural network models make them difficult to develop and train. The automatic parallel technology based on graph algorithms is one of the most promising methods to solve this problem, despite the low efficiency in the design, implementation, and execution of distributed parallel policies for large-scale neural network models. In this paper, we propose an adaptive distributed parallel training method based on the dynamic generation of critical DAG (directed acyclic graph) paths, called FD-DPS, to solve this efficiency problem. Firstly, the proposed model splits operators with the dimension of the tensor, which can expand the space available for model parallelism. Secondly, a dynamic critical path generation method is employed to determine node priority changes in the DAG of the neural network models. Finally, the model implements the optimal scheduling of critical paths based on the priority of the nodes, thereby improving the performance of parallel strategies. Our experiments show that FD-DPS can achieve 12.76% and 11.78% faster training on PnasNet_mobile and ResNet_200 models, respectively, compared with the MP-DPS and Fast methods.
41
Zhu, Cunchao, Muhao Chen, Changjun Fan, Guangquan Cheng e Yan Zhang. "Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks". Proceedings of the AAAI Conference on Artificial Intelligence 35, n.º 5 (18 de maio de 2021): 4732–40. http://dx.doi.org/10.1609/aaai.v35i5.16604.
Texto completo da fonteResumo:
Large knowledge graphs often grow to store temporal facts that model the dynamic relations or interactions of entities along the timeline. Since such temporal knowledge graphs often suffer from incompleteness, it is important to develop time-aware representation learning models that help to infer the missing temporal facts. While the temporal facts are typically evolving, it is observed that many facts often show a repeated pattern along the timeline, such as economic crises and diplomatic activities. This observation indicates that a model could potentially learn much from the known facts appeared in history. To this end, we propose a new representation learning model for temporal knowledge graphs, namely CyGNet, based on a novel time-aware copy-generation mechanism. CyGNet is not only able to predict future facts from the whole entity vocabulary, but also capable of identifying facts with repetition and accordingly predicting such future facts with reference to the known facts in the past. We evaluate the proposed method on the knowledge graph completion task using five benchmark datasets. Extensive experiments demonstrate the effectiveness of CyGNet for predicting future facts with repetition as well as de novo fact prediction.
42
Racković, Miloš, Miomir Vukobratović e Dusan Surla. "Generation of dynamic models of complex robotic mechanisms in symbolic form". Robotica 16, n.º 1 (janeiro de 1998): 23–36. http://dx.doi.org/10.1017/s0263574798000125.
Texto completo da fonteResumo:
A system to control a database is used for modelling of robotic mechanisms. This brings up the modelling process of robotic mechanisms to a higher level of abstraction and reduces the problem of numerical complexity reduction of the robotic mechanism model to database updating. Structural System Analysis was used to describe the functionality of the system for modelling of robotic mechanisms. The database model is presented by Extended Model Object-Connections, and all the object types for representation of mathematical expressions in the form of calculating graph are described in detail. The complete system is implemented and tested on the example of a robotic mechanism with six degrees of freedom and on the example of anthropomorphic locomotion robotic mechanism.
43
Su, Zejia, Qingnan Fan, Xuelin Chen, Oliver Van Kaick, Hui Huang e Ruizhen Hu. "Scene-Aware Activity Program Generation with Language Guidance". ACM Transactions on Graphics 42, n.º 6 (5 de dezembro de 2023): 1–16. http://dx.doi.org/10.1145/3618338.
Texto completo da fonteResumo:
We address the problem of scene-aware activity program generation, which requires decomposing a given activity task into instructions that can be sequentially performed within a target scene to complete the activity. While existing methods have shown the ability to generate rational or executable programs, generating programs with both high rationality and executability still remains a challenge. Hence, we propose a novel method where the key idea is to explicitly combine the language rationality of a powerful language model with dynamic perception of the target scene where instructions are executed, to generate programs with high rationality and executability. Our method iteratively generates instructions for the activity program. Specifically, a two-branch feature encoder operates on a language-based and graph-based representation of the current generation progress to extract language features and scene graph features, respectively. These features are then used by a predictor to generate the next instruction in the program. Subsequently, another module performs the predicted action and updates the scene for perception in the next iteration. Extensive evaluations are conducted on the VirtualHome-Env dataset, showing the advantages of our method over previous work. Key algorithmic designs are validated through ablation studies, and results on other types of inputs are also presented to show the generalizability of our method.
44
Ashaari, Azmirul, Tahir Ahmad e Wan Munirah Wan Mohamad. "Transformation of Pressurized Water Reactor (AP1000) to Fuzzy Graph". MATEMATIKA 34, n.º 2 (2 de dezembro de 2018): 235–44. http://dx.doi.org/10.11113/matematika.v34.n2.1028.
Texto completo da fonteResumo:
Pressurized water reactor (PWR) type AP1000 is a third generation of a nuclear power plant. The primary system of PWR using uranium dioxide to generate heat energy via fission process. The process influences temperature, pressure and pH value of water chemistry of the PWR. The aim of this paper is to transform the primary system of PWR using fuzzy autocatalytic set (FACS). In this work, the background of primary system of PWR and the properties of the model are provided. The simulation result, namely dynamic concentration of PWR is verified against published data.
45
Kim, Incheol. "Visual Experience-Based Question Answering with Complex Multimodal Environments". Mathematical Problems in Engineering 2020 (19 de novembro de 2020): 1–18. http://dx.doi.org/10.1155/2020/8567271.
Texto completo da fonteResumo:
This paper proposes a novel visual experience-based question answering problem (VEQA) and the corresponding dataset for embodied intelligence research that requires an agent to do actions, understand 3D scenes from successive partial input images, and answer natural language questions about its visual experiences in real time. Unlike the conventional visual question answering (VQA), the VEQA problem assumes both partial observability and dynamics of a complex multimodal environment. To address this VEQA problem, we propose a hybrid visual question answering system, VQAS, integrating a deep neural network-based scene graph generation model and a rule-based knowledge reasoning system. The proposed system can generate more accurate scene graphs for dynamic environments with some uncertainty. Moreover, it can answer complex questions through knowledge reasoning with rich background knowledge. Results of experiments using a photo-realistic 3D simulated environment, AI2-THOR, and the VEQA benchmark dataset prove the high performance of the proposed system.
46
Ivanovski, Aleksandar, Milos Jovanovik, Riste Stojanov e Dimitar Trajanov. "Knowledge Graph Based Recommender for Automatic Playlist Continuation". Information 14, n.º 9 (16 de setembro de 2023): 510. http://dx.doi.org/10.3390/info14090510.
Texto completo da fonteResumo:
In this work, we present a state-of-the-art solution for automatic playlist continuation through a knowledge graph-based recommender system. By integrating representational learning with graph neural networks and fusing multiple data streams, the system effectively models user behavior, leading to accurate and personalized recommendations. We provide a systematic and thorough comparison of our results with existing solutions and approaches, demonstrating the remarkable potential of graph-based representation in improving recommender systems. Our experiments reveal substantial enhancements over existing approaches, further validating the efficacy of this novel approach. Additionally, through comprehensive evaluation, we highlight the robustness of our solution in handling dynamic user interactions and streaming data scenarios, showcasing its practical viability and promising prospects for next-generation recommender systems.
47
Tu, Wenxuan, Sihang Zhou, Xinwang Liu, Xifeng Guo, Zhiping Cai, En Zhu e Jieren Cheng. "Deep Fusion Clustering Network". Proceedings of the AAAI Conference on Artificial Intelligence 35, n.º 11 (18 de maio de 2021): 9978–87. http://dx.doi.org/10.1609/aaai.v35i11.17198.
Texto completo da fonteResumo:
Deep clustering is a fundamental yet challenging task for data analysis. Recently we witness a strong tendency of combining autoencoder and graph neural networks to exploit structure information for clustering performance enhancement. However, we observe that existing literature 1) lacks a dynamic fusion mechanism to selectively integrate and refine the information of graph structure and node attributes for consensus representation learning; 2) fails to extract information from both sides for robust target distribution (i.e., “groundtruth” soft labels) generation. To tackle the above issues, we propose a Deep Fusion Clustering Network (DFCN). Specifically, in our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder for consensus representation learning. Also, a reliable target distribution generation measure and a triplet self-supervision strategy, which facilitate cross-modality information exploitation, are designed for network training. Extensive experiments on six benchmark datasets have demonstrated that the proposed DFCN consistently outperforms the state-of-the-art deep clustering methods.
48
RAHMOUNI, MAHER, KEVIN O’BRIEN e AHMED A. JERRAYA. "A LOOP-BASED SCHEDULING ALGORITHM FOR HARDWARE DESCRIPTION LANGUAGES". Parallel Processing Letters 04, n.º 03 (setembro de 1994): 351–64. http://dx.doi.org/10.1142/s0129626494000326.
Texto completo da fonteResumo:
This paper presents Dynamic Loop Scheduling (DLS), a loop-based algorithm that can efficiently schedule large, control-flow dominated designs. It compares favourably with results produced for traditional path-based approaches and at the same time requires much less overhead to implement. The high-performance of DLS is due mainly to the inclusion of loop feedback edges in the control-flow graph and the interruption of the path generation on the fly. The latter eliminates the generation of false paths thereby avoiding the path explosion problem.
49
Wang, Rongjie, Junyi Li, Yang Bai, Tianyi Zang e Yadong Wang. "BdBG: a bucket-based method for compressing genome sequencing data with dynamic de Bruijn graphs". PeerJ 6 (19 de outubro de 2018): e5611. http://dx.doi.org/10.7717/peerj.5611.
Texto completo da fonteResumo:
Dramatic increases in data produced by next-generation sequencing (NGS) technologies demand data compression tools for saving storage space. However, effective and efficient data compression for genome sequencing data has remained an unresolved challenge in NGS data studies. In this paper, we propose a novel alignment-free and reference-free compression method, BdBG, which is the first to compress genome sequencing data with dynamic de Bruijn graphs based on the data after bucketing. Compared with existing de Bruijn graph methods, BdBG only stored a list of bucket indexes and bifurcations for the raw read sequences, and this feature can effectively reduce storage space. Experimental results on several genome sequencing datasets show the effectiveness of BdBG over three state-of-the-art methods. BdBG is written in python and it is an open source software distributed under the MIT license, available for download at https://github.com/rongjiewang/BdBG.
50
Gong, Jibing, Cheng Wang, Zhiyong Zhao e Xinghao Zhang. "Automatic Generation of Meta-Path Graph for Concept Recommendation in MOOCs". Electronics 10, n.º 14 (13 de julho de 2021): 1671. http://dx.doi.org/10.3390/electronics10141671.
Texto completo da fonteResumo:
In MOOCs, generally speaking, curriculum designing, course selection, and knowledge concept recommendation are the three major steps that systematically instruct users to learn. This paper focuses on the knowledge concept recommendation in MOOCs, which recommends related topics to users to facilitate their online study. The existing approaches only consider the historical behaviors of users, but ignore various kinds of auxiliary information, which are also critical for user embedding. In addition, traditional recommendation models only consider the immediate user response to the recommended items, and do not explicitly consider the long-term interests of users. To deal with the above issues, this paper proposes AGMKRec, a novel reinforced concept recommendation model with a heterogeneous information network. We first clarify the concept recommendation in MOOCs as a reinforcement learning problem to offer a personalized and dynamic knowledge concept label list to users. To consider more auxiliary information of users, we construct a heterogeneous information network among users, courses, and concepts, and use a meta-path-based method which can automatically identify useful meta-paths and multi-hop connections to learn a new graph structure for learning effective node representations on a graph. Comprehensive experiments and analyses on a real-world dataset collected from XuetangX show that our proposed model outperforms some state-of-the-art methods.