Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Knowledge Graph (KG).
Articles de revues sur le sujet « Knowledge Graph (KG) »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleurs articles de revues pour votre recherche sur le sujet « Knowledge Graph (KG) ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les articles de revues sur diverses disciplines et organisez correctement votre bibliographie.
1
Hao, Wu, Jiao Menglin, Tian Guohui, Ma Qing, and Liu Guoliang. "R-KG: A Novel Method for Implementing a Robot Intelligent Service." AI 1, no. 1 (2020): 117–40. http://dx.doi.org/10.3390/ai1010006.
Texte intégralRésumé :
Aiming to solve the problem of environmental information being difficult to characterize when an intelligent service is used, knowledge graphs are used to express environmental information when performing intelligent services. Here, we specially design a kind of knowledge graph for environment expression referred to as a robot knowledge graph (R-KG). The main work of a R-KG is to integrate the diverse semantic information in the environment and pay attention to the relationship at the instance level. Also, through the efficient knowledge organization of a R-KG, robots can fully understand the environment. The R-KG firstly integrates knowledge from different sources to form a unified and standardized representation of a knowledge graph. Then, the deep logical relationship hidden in the knowledge graph is explored. To this end, a knowledge reasoning model based on a Markov logic network is proposed to realize the self-developmental ability of the knowledge graph and to further enrich it. Finally, as the strength of environment expression directly affects the efficiency of robots performing services, in order to verify the efficiency of the R-KG, it is used here as the semantic map that can be directly used by a robot for performing intelligent services. The final results prove that the R-KG can effectively express environmental information.
2
Khan, Arijit. "Knowledge Graphs Querying." ACM SIGMOD Record 52, no. 2 (2023): 18–29. http://dx.doi.org/10.1145/3615952.3615956.
Texte intégralRésumé :
Knowledge graphs (KGs) such as DBpedia, Freebase, YAGO, Wikidata, and NELL were constructed to store large-scale, real-world facts as (subject, predicate, object) triples - that can also be modeled as a graph, where a node (a subject or an object) represents an entity with attributes, and a directed edge (a predicate) is a relationship between two entities. Querying KGs is critical in web search, question answering (QA), semantic search, personal assistants, fact checking, and recommendation. While significant progress has been made on KG construction and curation, thanks to deep learning recently we have seen a surge of research on KG querying and QA. The objectives of our survey are two-fold. First, research on KG querying has been conducted by several communities, such as databases, data mining, semantic web, machine learning, information retrieval, and natural language processing (NLP), with different focus and terminologies; and also in diverse topics ranging from graph databases, query languages, join algorithms, graph patterns matching, to more sophisticated KG embedding and natural language questions (NLQs). We aim at uniting different interdisciplinary topics and concepts that have been developed for KG querying. Second, many recent advances on KG and query embedding, multimodal KG, and KG-QA come from deep learning, IR, NLP, and computer vision domains. We identify important challenges of KG querying that received less attention by graph databases, and by the DB community in general, e.g., incomplete KG, semantic matching, multimodal data, and NLQs. We conclude by discussing interesting opportunities for the data management community, for instance, KG as a unified data model and vector-based query processing.
3
Fang, Yin, Qiang Zhang, Haihong Yang, et al. "Molecular Contrastive Learning with Chemical Element Knowledge Graph." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 4 (2022): 3968–76. http://dx.doi.org/10.1609/aaai.v36i4.20313.
Texte intégralRésumé :
Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes self-supervision signals and has no requirements for human annotations. However, prior works fail to incorporate fundamental domain knowledge into graph semantics and thus ignore the correlations between atoms that have common attributes but are not directly connected by bonds. To address these issues, we construct a Chemical Element Knowledge Graph (KG) to summarize microscopic associations between elements and propose a novel Knowledge-enhanced Contrastive Learning (KCL) framework for molecular representation learning. KCL framework consists of three modules. The first module, knowledge-guided graph augmentation, augments the original molecular graph based on the Chemical Element KG. The second module, knowledge-aware graph representation, extracts molecular representations with a common graph encoder for the original molecular graph and a Knowledge-aware Message Passing Neural Network (KMPNN) to encode complex information in the augmented molecular graph. The final module is a contrastive objective, where we maximize agreement between these two views of molecular graphs. Extensive experiments demonstrated that KCL obtained superior performances against state-of-the-art baselines on eight molecular datasets. Visualization experiments properly interpret what KCL has learned from atoms and attributes in the augmented molecular graphs.
4
Bai, Liting, Lin Liu, Shengli Song, and Yueshen Xu. "NCR-KG: news community recommendation with knowledge graph." CCF Transactions on Pervasive Computing and Interaction 1, no. 4 (2019): 250–59. http://dx.doi.org/10.1007/s42486-019-00020-3.
Texte intégral
5
Tong, Peihao, Qifan Zhang, and Junjie Yao. "Leveraging Domain Context for Question Answering Over Knowledge Graph." Data Science and Engineering 4, no. 4 (2019): 323–35. http://dx.doi.org/10.1007/s41019-019-00109-w.
Texte intégralRésumé :
Abstract With the growing availability of different knowledge graphs in a variety of domains, question answering over knowledge graph (KG-QA) becomes a prevalent information retrieval approach. Current KG-QA methods usually resort to semantic parsing, search or neural matching models. However, they cannot well tackle increasingly long input questions and complex information needs. In this work, we propose a new KG-QA approach, leveraging the rich domain context in the knowledge graph. We incorporate the new approach with question and answer domain context descriptions. Specifically, for questions, we enrich them with users’ subsequent input questions within a session and expand the input question representation. For the candidate answers, we equip them with surrounding context structures, i.e., meta-paths within the targeting knowledge graph. On top of these, we design a cross-attention mechanism to improve the question and answer matching performance. An experimental study on real datasets verifies these improvements. The new approach is especially beneficial for specific knowledge graphs with complex questions.
6
Swapnil, S. Mahure. "Missing Link Prediction in Art Knowledge Graph using Representation Learning." International Journal of Innovative Technology and Exploring Engineering (IJITEE) 13, no. 5 (2024): 30–33. https://doi.org/10.35940/ijitee.J9264.13050424.
Texte intégralRésumé :
<strong>Abstract:</strong> Knowledge graphs are an important evolving field in Artificial Intelligence domain which has multiple applications such as in question answering, important information retrieval, information recommendation, Natural language processing etc. Knowledge graph has one big limitation i.e. Incompleteness, it is due to because of real world data are dynamic and continues evolving. This incompleteness of Knowledge graph can be overcome or minimized by using representation learning models. There are several models which are classified on the base of translation distance, semantic information and NN (Neural Network) based. Earlier the various embedding models are test on mostly two well-known datasets WN18RR & FB15k-237. In this paper, new dataset i.e. ArtGraph has been utilised for link prediction using representation learning models to enhance the utilization of ArtGraph in various domains. Experimental results shown ConvKB performed better over the other models for link prediction task.
7
Tian, Xin, and Yuan Meng. "Relgraph: A Multi-Relational Graph Neural Network Framework for Knowledge Graph Reasoning Based on Relation Graph." Applied Sciences 14, no. 7 (2024): 3122. http://dx.doi.org/10.3390/app14073122.
Texte intégralRésumé :
Multi-relational graph neural networks (GNNs) have found widespread application in tasks involving enhancing knowledge representation and knowledge graph (KG) reasoning. However, existing multi-relational GNNs still face limitations in modeling the exchange of information between predicates. To address these challenges, we introduce Relgraph, a novel KG reasoning framework. This framework introduces relation graphs to explicitly model the interactions between different relations, enabling more comprehensive and accurate handling of representation learning and reasoning tasks on KGs. Furthermore, we design a machine learning algorithm based on the attention mechanism to simultaneously optimize the original graph and its corresponding relation graph. Benchmark and experimental results on large-scale KGs demonstrate that the Relgraph framework improves KG reasoning performance. The framework exhibits a certain degree of versatility and can be seamlessly integrated with various traditional translation models.
8
Kejriwal, Mayank. "Knowledge Graphs: A Practical Review of the Research Landscape." Information 13, no. 4 (2022): 161. http://dx.doi.org/10.3390/info13040161.
Texte intégralRésumé :
Knowledge graphs (KGs) have rapidly emerged as an important area in AI over the last ten years. Building on a storied tradition of graphs in the AI community, a KG may be simply defined as a directed, labeled, multi-relational graph with some form of semantics. In part, this has been fueled by increased publication of structured datasets on the Web, and well-publicized successes of large-scale projects such as the Google Knowledge Graph and the Amazon Product Graph. However, another factor that is less discussed, but which has been equally instrumental in the success of KGs, is the cross-disciplinary nature of academic KG research. Arguably, because of the diversity of this research, a synthesis of how different KG research strands all tie together could serve a useful role in enabling more ‘moonshot’ research and large-scale collaborations. This review of the KG research landscape attempts to provide such a synthesis by first showing what the major strands of research are, and how those strands map to different communities, such as Natural Language Processing, Databases and Semantic Web. A unified framework is suggested in which to view the distinct, but overlapping, foci of KG research within these communities.
9
Yan, Yuchen, Lihui Liu, Yikun Ban, Baoyu Jing, and Hanghang Tong. "Dynamic Knowledge Graph Alignment." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 5 (2021): 4564–72. http://dx.doi.org/10.1609/aaai.v35i5.16585.
Texte intégralRésumé :
Knowledge graph (KG for short) alignment aims at building a complete KG by linking the shared entities across complementary KGs. Existing approaches assume that KGs are static, despite the fact that almost every KG evolves over time. In this paper, we introduce the task of dynamic knowledge graph alignment, the main challenge of which is how to efficiently update entity embeddings for the evolving graph topology. Our key insight is to view the parameter matrix of GCN as a feature transformation operator and decouple the transformation process from the aggregation process. Based on that, we first propose a novel base algorithm (DINGAL-B) with topology-invariant mask gate and highway gate, which consistently outperforms 14 existing knowledge graph alignment methods in the static setting. More importantly, it naturally leads to two effective and efficient algorithms to align dynamic knowledge graph, including (1) DINGAL-O which leverages previous parameter matrices to update the embeddings of affected entities; and (2) DINGAL-U which resorts to newly obtained anchor links to fine-tune parameter matrices. Compared with their static counterpart (DINGAL-B), DINGAL-U and DINGAL-O are 10× and 100× faster respectively, with little alignment accuracy loss.
10
Zuo, H., Y. Yin, and P. Childs. "Patent-KG: Patent Knowledge Graph Extraction for Engineering Design." Proceedings of the Design Society 2 (May 2022): 821–30. http://dx.doi.org/10.1017/pds.2022.84.
Texte intégralRésumé :
AbstractThis paper builds a patent-based knowledge graph, patent-KG, to represent the knowledge facts in patents for engineering design. The arising patent-KG approach proposes a new unsupervised mechanism to extract knowledge facts in a patent, by searching the attention graph in language models. The extracted entities are compared with other benchmarks in the criteria of recall rate. The result reaches the highest 0.8 recall rate in the standard list of mechanical engineering related technical terms, which means the highest coverage of engineering words.
11
Bellomarini, Luigi, Marco Benedetti, Andrea Gentili, Davide Magnanimi, and Emanuel Sallinger. "KG-Roar: Interactive Datalog-Based Reasoning on Virtual Knowledge Graphs." Proceedings of the VLDB Endowment 16, no. 12 (2023): 4014–17. http://dx.doi.org/10.14778/3611540.3611609.
Texte intégralRésumé :
Logic-based Knowledge Graphs (KGs) are gaining momentum in academia and industry thanks to the rise of expressive and efficient languages for Knowledge Representation and Reasoning (KRR). These languages accurately express business rules, through which valuable new knowledge is derived. A versatile and scalable backend reasoner, like Vadalog, a state-of-the-art system for logic-based KGs---based on an extension of Datalog---executes the reasoning. In this demo, we present KG-Roar, a web-based interactive development and navigation environment for logical KGs. The system lets the user augment an input graph database with intensional definitions of new nodes and edges and turn it into a KG, via the metaphor of reasoning widgets---user-defined or off-the-shelf code snippets that capture business definitions in the Vadalog language. Then, the user can seamlessly browse the original and the derived nodes and edges within a "Virtual Knowledge Graph", which is reasoned upon and generated interactively at runtime, thanks to the scalability and responsiveness of Vadalog. KG-Roar is domain-independent but domain aware, as exploration controls are contextually generated based on the intensional definitions. We walk the audience through KG-Roar showcasing the construction of certain business definitions and putting it into action on a real-world financial KG, from our work with the Bank of Italy.
12
Monka, Sebastian, Lavdim Halilaj, and Achim Rettinger. "A survey on visual transfer learning using knowledge graphs." Semantic Web 13, no. 3 (2022): 477–510. http://dx.doi.org/10.3233/sw-212959.
Texte intégralRésumé :
The information perceived via visual observations of real-world phenomena is unstructured and complex. Computer vision (CV) is the field of research that attempts to make use of that information. Recent approaches of CV utilize deep learning (DL) methods as they perform quite well if training and testing domains follow the same underlying data distribution. However, it has been shown that minor variations in the images that occur when these methods are used in the real world can lead to unpredictable and catastrophic errors. Transfer learning is the area of machine learning that tries to prevent these errors. Especially, approaches that augment image data using auxiliary knowledge encoded in language embeddings or knowledge graphs (KGs) have achieved promising results in recent years. This survey focuses on visual transfer learning approaches using KGs, as we believe that KGs are well suited to store and represent any kind of auxiliary knowledge. KGs can represent auxiliary knowledge either in an underlying graph-structured schema or in a vector-based knowledge graph embedding. Intending to enable the reader to solve visual transfer learning problems with the help of specific KG-DL configurations we start with a description of relevant modeling structures of a KG of various expressions, such as directed labeled graphs, hypergraphs, and hyper-relational graphs. We explain the notion of feature extractor, while specifically referring to visual and semantic features. We provide a broad overview of knowledge graph embedding methods and describe several joint training objectives suitable to combine them with high dimensional visual embeddings. The main section introduces four different categories on how a KG can be combined with a DL pipeline: 1) Knowledge Graph as a Reviewer; 2) Knowledge Graph as a Trainee; 3) Knowledge Graph as a Trainer; and 4) Knowledge Graph as a Peer. To help researchers find meaningful evaluation benchmarks, we provide an overview of generic KGs and a set of image processing datasets and benchmarks that include various types of auxiliary knowledge. Last, we summarize related surveys and give an outlook about challenges and open issues for future research.
13
Cao, Keyan, and Chuang Zheng. "TBRm: A Time Representation Method for Industrial Knowledge Graph." Applied Sciences 12, no. 22 (2022): 11316. http://dx.doi.org/10.3390/app122211316.
Texte intégralRésumé :
With the development of the artificial intelligence industry, Knowledge Graph (KG), as a concise and intuitive data presentation form, has received extensive attention and research from both academia and industry in recent years. At the same time, developments in the Internet of Things (IoT) have empowered modern industries to implement large-scale IoT ecosystems, such as the Industrial Internet of Things (IIoT). Using knowledge graphs (KG) to process data from the Industrial Internet of Things (IIoT) is a research field worthy of attention, but most of the researched knowledge graph technologies are mainly concentrated in the field of static knowledge graphs, which are composed of triples. In fact, many graphs also contain some dynamic information, such as time changes at points and time changes at edges; such knowledge graphs are called Temporal Knowledge Graphs (TKGs). We consider the temporal knowledge graph based on the projection and change of space. In order to combine the temporal information, we propose a new representation of the temporal knowledge graph, namely TBRm, which increases the temporal dimension of the translational distance model and utilizes relational predicates in time add representation in time dimension. We evaluate the proposed method on knowledge graph completion tasks using four benchmark datasets. Experiments demonstrate the effectiveness of TBRm representation in the temporal dimension. At the same time, it is also practiced on a network security data set of the Industrial Internet of Things. The practical results prove that the TBRm method can achieve good performance in terms of the degree of harm to IIoT network security.
14
Wang, Yu, Nedim Lipka, Ryan A. Rossi, Alexa Siu, Ruiyi Zhang, and Tyler Derr. "Knowledge Graph Prompting for Multi-Document Question Answering." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 17 (2024): 19206–14. http://dx.doi.org/10.1609/aaai.v38i17.29889.
Texte intégralRésumé :
The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design and retrieval augmented generation for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA.
15
Liu, Ye, Yao Wan, Lifang He, Hao Peng, and Philip S. Yu. "KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 7 (2021): 6418–25. http://dx.doi.org/10.1609/aaai.v35i7.16796.
Texte intégralRésumé :
Generative commonsense reasoning which aims to empower machines to generate sentences with the capacity of reasoning over a set of concepts is a critical bottleneck for text generation. Even the state-of-the-art pre-trained language generation models struggle at this task and often produce implausible and anomalous sentences. One reason is that they rarely consider incorporating the knowledge graph which can provide rich relational information among the commonsense concepts. To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. Moreover, KG-BART can leverage the graph attention to aggregate the rich concept semantics that enhances the model generalization on unseen concept sets. Experiments on benchmark CommonGen dataset verify the effectiveness of our proposed approach by comparing with several strong pre-trained language generation models, particularly KG-BART outperforms BART by 5.80, 4.60, in terms of BLEU-3, 4. Moreover, we also show that the generated context by our model can work as background scenarios to benefit downstream commonsense QA tasks.
16
Zhang, Peng, Yi Bu, Peng Jiang, et al. "Toward a Coronavirus Knowledge Graph." Genes 12, no. 7 (2021): 998. http://dx.doi.org/10.3390/genes12070998.
Texte intégralRésumé :
This study builds a coronavirus knowledge graph (KG) by merging two information sources. The first source is Analytical Graph (AG), which integrates more than 20 different public datasets related to drug discovery. The second source is CORD-19, a collection of published scientific articles related to COVID-19. We combined both chemo genomic entities in AG with entities extracted from CORD-19 to expand knowledge in the COVID-19 domain. Before populating KG with those entities, we perform entity disambiguation on CORD-19 collections using Wikidata. Our newly built KG contains at least 21,700 genes, 2500 diseases, 94,000 phenotypes, and other biological entities (e.g., compound, species, and cell lines). We define 27 relationship types and use them to label each edge in our KG. This research presents two cases to evaluate the KG’s usability: analyzing a subgraph (ego-centered network) from the angiotensin-converting enzyme (ACE) and revealing paths between biological entities (hydroxychloroquine and IL-6 receptor; chloroquine and STAT1). The ego-centered network captured information related to COVID-19. We also found significant COVID-19-related information in top-ranked paths with a depth of three based on our path evaluation.
17
Yang, Zhenyu, Lei Wu, Peian Wen, and Peng Chen. "Visual Question Answering reasoning with external knowledge based on bimodal graph neural network." Electronic Research Archive 31, no. 4 (2023): 1948–65. http://dx.doi.org/10.3934/era.2023100.
Texte intégralRésumé :
<abstract><p>Visual Question Answering (VQA) with external knowledge requires external knowledge and visual content to answer questions about images. The defect of existing VQA solutions is that they need to identify task-related information in the obtained pictures, questions, and knowledge graphs. It is necessary to properly fuse and embed the information between different modes identified, to reduce the noise and difficulty in cross-modality reasoning of VQA models. However, this process of rationally integrating information between different modes and joint reasoning to find relevant evidence to correctly predict the answer to the question still deserves further study. This paper proposes a bimodal Graph Neural Network model combining pre-trained Language Models and Knowledge Graphs (BIGNN-LM-KG). Researchers built the concepts graph by the images and questions concepts separately. In constructing the concept graph, we used the combined reasoning advantages of LM+KG. Specifically, use KG to jointly infer the images and question entity concepts to build a concept graph. Use LM to calculate the correlation score to screen the nodes and paths of the concept graph. Then, we form a visual graph from the visual and spatial features of the filtered image entities. We use the improved GNN to learn the representation of the two graphs and to predict the most likely answer by fusing the information of two different modality graphs using a modality fusion GNN. On the common dataset of VQA, the model we proposed obtains good experiment results. It also verifies the validity of each component in the model and the interpretability of the model.</p></abstract>
18
Wang, Meihong, Linling Qiu, and Xiaoli Wang. "A Survey on Knowledge Graph Embeddings for Link Prediction." Symmetry 13, no. 3 (2021): 485. http://dx.doi.org/10.3390/sym13030485.
Texte intégralRésumé :
Knowledge graphs (KGs) have been widely used in the field of artificial intelligence, such as in information retrieval, natural language processing, recommendation systems, etc. However, the open nature of KGs often implies that they are incomplete, having self-defects. This creates the need to build a more complete knowledge graph for enhancing the practical utilization of KGs. Link prediction is a fundamental task in knowledge graph completion that utilizes existing relations to infer new relations so as to build a more complete knowledge graph. Numerous methods have been proposed to perform the link-prediction task based on various representation techniques. Among them, KG-embedding models have significantly advanced the state of the art in the past few years. In this paper, we provide a comprehensive survey on KG-embedding models for link prediction in knowledge graphs. We first provide a theoretical analysis and comparison of existing methods proposed to date for generating KG embedding. Then, we investigate several representative models that are classified into five categories. Finally, we conducted experiments on two benchmark datasets to report comprehensive findings and provide some new insights into the strengths and weaknesses of existing models.
19
Yang, Tong, Yifei Wang, Long Sha, Jan Engelbrecht, and Pengyu Hong. "Knowledgebra: An Algebraic Learning Framework for Knowledge Graph." Machine Learning and Knowledge Extraction 4, no. 2 (2022): 432–45. http://dx.doi.org/10.3390/make4020019.
Texte intégralRésumé :
Knowledge graph (KG) representation learning aims to encode entities and relations into dense continuous vector spaces such that knowledge contained in a dataset could be consistently represented. Dense embeddings trained from KG datasets benefit a variety of downstream tasks such as KG completion and link prediction. However, existing KG embedding methods fell short to provide a systematic solution for the global consistency of knowledge representation. We developed a mathematical language for KG based on an observation of their inherent algebraic structure, which we termed as Knowledgebra. By analyzing five distinct algebraic properties, we proved that the semigroup is the most reasonable algebraic structure for the relation embedding of a general knowledge graph. We implemented an instantiation model, SemE, using simple matrix semigroups, which exhibits state-of-the-art performance on standard datasets. Moreover, we proposed a regularization-based method to integrate chain-like logic rules derived from human knowledge into embedding training, which further demonstrates the power of the developed language. As far as we know, by applying abstract algebra in statistical learning, this work develops the first formal language for general knowledge graphs, and also sheds light on the problem of neural-symbolic integration from an algebraic perspective.
20
Ni, Bo, Yu Wang, Lu Cheng, Erik Blasch, and Tyler Derr. "Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 12 (2025): 12417–25. https://doi.org/10.1609/aaai.v39i12.33353.
Texte intégralRésumé :
Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, e.g., KG-based retrieval-augmented framework. However, current KG-LLM frameworks lack rigorous uncertainty estimation, limiting their reliable deployment in applications where the cost of errors is significant. Directly incorporating uncertainty quantification into KG-LLM frameworks presents a challenge due to their more complex architectures and the intricate interactions between the knowledge graph and language model components. To address this crucial gap, we propose a new trustworthy KG-LLM framework, UAG (Uncertainty Aware Knowledge-Graph Reasoning), which incorporates uncertainty quantification into the KG-LLM framework. We design an uncertainty-aware multi-step reasoning framework that leverages conformal prediction to provide a theoretical guarantee on the prediction set. To manage the error rate of the multi-step process, we additionally introduce an error rate control module to adjust the error rate within the individual components. Extensive experiments show that UAG can achieve any pre-defined coverage rate while reducing the prediction set/interval size by 40% on average over the baselines.
21
Garifo, Giovanni, Giuseppe Futia, Antonio Vetrò, and Juan Carlos De Martin. "The Geranium Platform: A KG-Based System for Academic Publications." Information 12, no. 9 (2021): 366. http://dx.doi.org/10.3390/info12090366.
Texte intégralRésumé :
Knowledge Graphs (KGs) have emerged as a core technology for incorporating human knowledge because of their capability to capture the relational dimension of information and of its semantic properties. The nature of KGs meets one of the vocational pursuits of academic institutions, which is sharing their intellectual output, especially publications. In this paper, we describe and make available the Polito Knowledge Graph (PKG) –which semantically connects information on more than 23,000 publications and 34,000 authors– and Geranium, a semantic platform that leverages the properties of the PKG to offer advanced services for search and exploration. In particular, we describe the Geranium recommendation system, which exploits Graph Neural Networks (GNNs) to suggest collaboration opportunities between researchers of different disciplines. This work integrates the state of the art because we use data from a real application in the scholarly domain, while the current literature still explores the combination of KGs and GNNs in a prototypal context using synthetic data. The results shows that the fusion of these technologies represents a promising approach for recommendation and metadata inference in the scholarly domain.
22
Goel, Rishab, Seyed Mehran Kazemi, Marcus Brubaker, and Pascal Poupart. "Diachronic Embedding for Temporal Knowledge Graph Completion." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 3988–95. http://dx.doi.org/10.1609/aaai.v34i04.5815.
Texte intégralRésumé :
Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been proposed to infer new facts for a KG based on the existing ones–a problem known as KG completion. KG embedding approaches have proved effective for KG completion, however, they have been developed mostly for static KGs. Developing temporal KG embedding models is an increasingly important problem. In this paper, we build novel models for temporal KG completion through equipping static models with a diachronic entity embedding function which provides the characteristics of entities at any point in time. This is in contrast to the existing temporal KG embedding approaches where only static entity features are provided. The proposed embedding function is model-agnostic and can be potentially combined with any static model. We prove that combining it with SimplE, a recent model for static KG embedding, results in a fully expressive model for temporal KG completion. Our experiments indicate the superiority of our proposal compared to existing baselines.
23
Shi, Xiujin, Jun Hu, Naiwen Sun, and Shoujian Yu. "TrEKBQA:Traversing Knowledge Graph Embedding for Multi-hop Knowledge Base Question Answering." Journal of Physics: Conference Series 2424, no. 1 (2023): 012027. http://dx.doi.org/10.1088/1742-6596/2424/1/012027.
Texte intégralRésumé :
Abstract Recent research apply KG embedding to multi-hop Knowledge Base Question Answering(KBQA) to predict missing links, however, it is often affected by the skewed distribution of nodes in the knowledge graph, resulting in poor generalization of the model. Therefore, we propose a method TrEKBQA based on traversing the knowledge graph embedding space for multi-hop KBQA, which performs path traversal in the KG embedding space instead of KG itself for link prediction to complete the knowledge graph, thus improving the accuracy of multi-hop KBQA.TrEKBQA model complex relationships using correlations between individual links and longer paths connecting the same pair of entities to traverse the KG embedding space to mitigate the effects of biased distribution of nodes and improve the performance of link prediction. In the pre-processing process, TrEKBQA uses the PRN algorithm to extract subgraphs related to the problem entity to reduce the number of target entities. Through experiments on multiple benchmark datasets, we demonstrate the effectiveness of TrEKBQA on KBQA tasks.
24
Zhang, Chuxu, Huaxiu Yao, Chao Huang, Meng Jiang, Zhenhui Li, and Nitesh V. Chawla. "Few-Shot Knowledge Graph Completion." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 03 (2020): 3041–48. http://dx.doi.org/10.1609/aaai.v34i03.5698.
Texte intégralRésumé :
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i.e., head-tail entity pairs) for every relation. The real case is that for most of the relations, very few entity pairs are available. Existing work of one-shot learning limits method generalizability for few-shot scenarios and does not fully use the supervisory information; however, few-shot KG completion has not been well studied yet. In this work, we propose a novel few-shot relation learning model (FSRL) that aims at discovering facts of new relations with few-shot references. FSRL can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few-shot references, and match similar entity pairs of reference set for every relation. Extensive experiments on two public datasets demonstrate that FSRL outperforms the state-of-the-art.
25
Liu, Rui, Rong Fu, Kang Xu, Xuanzhe Shi, and Xiaoning Ren. "A Review of Knowledge Graph-Based Reasoning Technology in the Operation of Power Systems." Applied Sciences 13, no. 7 (2023): 4357. http://dx.doi.org/10.3390/app13074357.
Texte intégralRésumé :
Knowledge graph (KG) technology is a newly emerged knowledge representation method in the field of artificial intelligence. Knowledge graphs can form logical mappings from cluttered data and establish triadic relationships between entities. Accurate derivation and reasoning of knowledge graphs play an important role in guiding power equipment operation and decision-making. Due to the complex and weak relations from multi-source heterogeneous data, the use of KGs has become popular in research to represent potential information in power knowledge reasoning. In this review, we first summarize the key technologies of knowledge graph representation and learning. Then, based on the complexity and real-time changes of power system operation and maintenance, we present multiple data processing, knowledge representation learning, and the graph construction process. In three typical power operation and fault decision application scenarios, we investigate current algorithms in power KG acquisition, representation embedding, and knowledge completion to illustrate accurate and exhaustive recommendations. Thus, using KGs to provide reference solutions and decision guidance has a significant role in improving the efficiency of power system operations. Finally, we summarize the achievements and difficulties of current research and give an outlook for future, promising roles of KG in power systems.
26
Wang, Kai, Yuwei Xu, and Siqiang Luo. "TIGER: Training Inductive Graph Neural Network for Large-Scale Knowledge Graph Reasoning." Proceedings of the VLDB Endowment 17, no. 10 (2024): 2459–72. http://dx.doi.org/10.14778/3675034.3675039.
Texte intégralRésumé :
Knowledge Graph (KG) Reasoning plays a vital role in various applications by predicting missing facts from existing knowledge. Inductive KG reasoning approaches based on Graph Neural Networks (GNNs) have shown impressive performance, particularly when reasoning with unseen entities and dynamic KGs. However, such state-of-the-art KG reasoning approaches encounter efficiency and scalability challenges on large-scale KGs due to the high computational costs associated with subgraph extraction - a key component in inductive KG reasoning. To address the computational challenge, we introduce TIGER, an inductive GNN training framework tailored for large-scale KG reasoning. TIGER employs a novel, efficient streaming procedure that facilitates rapid subgraph slicing and dynamic subgraph caching to minimize the cost of subgraph extraction. The fundamental challenge in TIGER lies in the optimal subgraph slicing problem, which we prove to be NP-hard. We propose a novel two-stage algorithm SiGMa to solve the problem practically. By decoupling the complicated problem into two classical ones, SiGMa achieves low computational complexity and high slice reuse. We also propose four new benchmarks for robust evaluation of large-scale inductive KG reasoning, the biggest of which performs on the Freebase KG (encompassing 86M entities, 285M edges). Through comprehensive experiments on state-of-the-art GNN-based KG reasoning models, we demonstrate that TIGER significantly reduces the running time of subgraph extraction, achieving an average 3.7× speedup relative to the basic training procedure.
27
Choi, Seungmin, and Yuchul Jung. "Knowledge Graph Construction: Extraction, Learning, and Evaluation." Applied Sciences 15, no. 7 (2025): 3727. https://doi.org/10.3390/app15073727.
Texte intégralRésumé :
A Knowledge Graph (KG), which structurally represents entities (nodes) and relationships (edges), offers a powerful and flexible approach to knowledge representation in the field of Artificial Intelligence (AI). KGs have been increasingly applied in various domains—such as natural language processing (NLP), recommendation systems, knowledge search, and medical diagnostics—spurring continuous research on effective methods for their construction and maintenance. Recently, efforts to combine large language models (LLMs), particularly those aimed at managing hallucination symptoms, with KGs have gained attention. Consequently, new approaches have emerged in each phase of KG development, including Extraction, Learning Paradigm, and Evaluation Methodology. In this paper, we focus on major publications released after 2022 to systematically examine the process of KG construction along three core dimensions: Extraction, Learning Paradigm, and Evaluation Methodology. Specifically, we investigate (1) large-scale data preprocessing and multimodal extraction techniques in the KG Extraction domain, (2) the refinement of traditional embedding methods and the application of cutting-edge techniques—such as Graph Neural Networks, Transformers, and LLMs—in the KG Learning domain, and (3) both intrinsic and extrinsic metrics in the KG Evaluation domain, as well as various approaches to ensure interpretability and reliability.
28
Gao, Zhenxiang, Pingjian Ding, and Rong Xu. "KG-Predict: A knowledge graph computational framework for drug repurposing." Journal of Biomedical Informatics 132 (August 2022): 104133. http://dx.doi.org/10.1016/j.jbi.2022.104133.
Texte intégral
29
Gu, Tianlong, Haohong Liang, Chenzhong Bin, and Liang Chang. "Combining user-end and item-end knowledge graph learning for personalized recommendation." Journal of Intelligent & Fuzzy Systems 40, no. 5 (2021): 9213–25. http://dx.doi.org/10.3233/jifs-201635.
Texte intégralRésumé :
How to accurately model user preferences based on historical user behaviour and auxiliary information is of great importance in personalized recommendation tasks. Among all types of auxiliary information, knowledge graphs (KGs) are an emerging type of auxiliary information with nodes and edges that contain rich structural information and semantic information. Many studies prove that incorporating KG into personalized recommendation tasks can effectively improve the performance, rationality and interpretability of recommendations. However, existing methods either explore the independent meta-paths for user-item pairs in KGs or use a graph convolution network on all KGs to obtain embeddings for users and items separately. Although both types of methods have respective effects, the former cannot fully capture the structural information of user-item pairs in KGs, while the latter ignores the mutual effect between the target user and item during the embedding learning process. To alleviate the shortcomings of these methods, we design a graph convolution-based recommendation model called Combining User-end and Item-end Knowledge Graph Learning (CUIKG), which aims to capture the relevance between users’ personalized preferences and items by jointly mining the associated attribute information in their respective KG. Specifically, we describe user embedding from a user KG and then introduce user embedding, which contains the user profile into the item KG, to describe item embedding with the method of Graph Convolution Network. Finally, we predict user preference probability for a given item via multilayer perception. CUIKG describes the connection between user-end KG and item-end KG, and mines the structural and semantic information present in KG. Experimental results with two real-world datasets demonstrate the superiority of the proposed method over existing methods.
30
Yang, Xu, Ziyi Huan, Yisong Zhai, and Ting Lin. "Research of Personalized Recommendation Technology Based on Knowledge Graphs." Applied Sciences 11, no. 15 (2021): 7104. http://dx.doi.org/10.3390/app11157104.
Texte intégralRésumé :
Nowadays, personalized recommendation based on knowledge graphs has become a hot spot for researchers due to its good recommendation effect. In this paper, we researched personalized recommendation based on knowledge graphs. First of all, we study the knowledge graphs’ construction method and complete the construction of the movie knowledge graphs. Furthermore, we use Neo4j graph database to store the movie data and vividly display it. Then, the classical translation model TransE algorithm in knowledge graph representation learning technology is studied in this paper, and we improved the algorithm through a cross-training method by using the information of the neighboring feature structures of the entities in the knowledge graph. Furthermore, the negative sampling process of TransE algorithm is improved. The experimental results show that the improved TransE model can more accurately vectorize entities and relations. Finally, this paper constructs a recommendation model by combining knowledge graphs with ranking learning and neural network. We propose the Bayesian personalized recommendation model based on knowledge graphs (KG-BPR) and the neural network recommendation model based on knowledge graphs (KG-NN). The semantic information of entities and relations in knowledge graphs is embedded into vector space by using improved TransE method, and we compare the results. The item entity vectors containing external knowledge information are integrated into the BPR model and neural network, respectively, which make up for the lack of knowledge information of the item itself. Finally, the experimental analysis is carried out on MovieLens-1M data set. The experimental results show that the two recommendation models proposed in this paper can effectively improve the accuracy, recall, F1 value and MAP value of recommendation.
31
Yuan, Xu, Jiaxi Chen, Yingbo Wang, et al. "Semantic-Enhanced Knowledge Graph Completion." Mathematics 12, no. 3 (2024): 450. http://dx.doi.org/10.3390/math12030450.
Texte intégralRésumé :
Knowledge graphs (KGs) serve as structured representations of knowledge, comprising entities and relations. KGs are inherently incomplete, sparse, and have a strong need for completion. Although many knowledge graph embedding models have been designed for knowledge graph completion, they predominantly focus on capturing observable correlations between entities. Due to the sparsity of KGs, potential semantic correlations are challenging to capture. To tackle this problem, we propose a model entitled semantic-enhanced knowledge graph completion (SE-KGC). SE-KGC effectively addresses the issue by incorporating predefined semantic patterns, enabling the capture of semantic correlations between entities and enhancing features for representation learning. To implement this approach, we employ a multi-relational graph convolution network encoder, which effectively encodes the KG. Subsequently, we utilize a scoring decoder to evaluate triplets. Experimental results demonstrate that our SE-KGC model outperforms other state-of-the-art methods in link-prediction tasks across three datasets. Specifically, compared to the baselines, SE-KGC achieved improvements of 11.7%, 1.05%, and 2.30% in terms of MRR on these three datasets. Furthermore, we present a comprehensive analysis of the contributions of different semantic patterns, and find that entities with higher connectivity play a pivotal role in effectively capturing and characterizing semantic information.
32
Li, Tongxin, Xiaobo Li, Fei Wang, Weiping Wang, and Tao Wang. "Confidence Prediction Based on Uncertain Knowledge Graph Structure Embedding." Journal of Physics: Conference Series 2833, no. 1 (2024): 012001. http://dx.doi.org/10.1088/1742-6596/2833/1/012001.
Texte intégralRésumé :
Abstract The development of large-scale knowledge graphs (KGs) has given rise to uncertain relational facts, leading to research on uncertain knowledge graph (KG) embeddings. While various studies have been conducted on the task of uncertain KG embeddings, they often employ simplistic scoring functions based on the internal interaction information among triplets to fit confidence scores, neglecting the rich neighborhood information. In light of this, we propose a novel model UKGSE for uncertain KG embeddings that captures the subgraph structural features formed by the neighbors of triplets, aiming to predict confidence scores for triplets. To validate the effectiveness of our model, we conduct confidence prediction tasks on benchmark datasets. The experimental results indicate that the performance of our proposed model surpasses mainstream embedding methods.
33
Zhu, Yueqin, Wenwen Zhou, Yang Xu, Ji Liu, and Yongjie Tan. "Intelligent Learning for Knowledge Graph towards Geological Data." Scientific Programming 2017 (2017): 1–13. http://dx.doi.org/10.1155/2017/5072427.
Texte intégralRésumé :
Knowledge graph (KG) as a popular semantic network has been widely used. It provides an effective way to describe semantic entities and their relationships by extending ontology in the entity level. This article focuses on the application of KG in the traditional geological field and proposes a novel method to construct KG. On the basis of natural language processing (NLP) and data mining (DM) algorithms, we analyze those key technologies for designing a KG towards geological data, including geological knowledge extraction and semantic association. Through this typical geological ontology extracting on a large number of geological documents and open linked data, the semantic interconnection is achieved, KG framework for geological data is designed, application system of KG towards geological data is constructed, and dynamic updating of the geological information is completed accordingly. Specifically, unsupervised intelligent learning method using linked open data is incorporated into the geological document preprocessing, which generates a geological domain vocabulary ultimately. Furthermore, some application cases in the KG system are provided to show the effectiveness and efficiency of our proposed intelligent learning approach for KG.
34
Tian, Shiyu, Shuyue Xing, Xingrui Li, et al. "A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 24 (2025): 25291–99. https://doi.org/10.1609/aaai.v39i24.34716.
Texte intégralRésumé :
Retrieval Augmented Generation (RAG) with Knowledge Graphs (KGs) is an effective way to enhance Large Language Models (LLMs). Due to the natural discrepancy between structured KGs and sequential LLMs, KGs must be linearized to text before being inputted into LLMs, leading to the problem of KG Alignment with LLMs (KGA). However, recent KG+RAG methods only consider KGA as a simple step without comprehensive and in-depth explorations, leaving three essential problems unclear: (1) What are the factors and their effects in KGA? (2) How do LLMs understand KGs? (3) How to improve KG+RAG by KGA? To fill this gap, we conduct systematic explorations on KGA, where we first define the problem of KGA and subdivide it into the graph transformation phase (graph-to-graph) and the linearization phase (graph-to-text). In the graph transformation phase, we study graph features at the node, edge, and full graph levels from low to high granularity. In the linearization phase, we study factors on formats, orders, and templates from structural to token levels. We conduct substantial experiments on 15 typical LLMs and three common datasets. Our main findings include: (1) The centrality of the KG affects the final generation; formats have the greatest impact on KGA; orders are model-dependent, without an optimal order adapting for all models; the templates with special token separators are better. (2) LLMs understand KGs by a unique mechanism, different from processing natural sentences, and separators play an important role. (3) We achieved 7.3% average performance improvements on four common LLMs on the KGQA task by combining the optimal factors to enhance KGA.
35
Zhao, Ruilin, Feng Zhao, Liang Hu, and Guandong Xu. "Graph Reasoning Transformers for Knowledge-Aware Question Answering." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 17 (2024): 19652–60. http://dx.doi.org/10.1609/aaai.v38i17.29938.
Texte intégralRésumé :
Augmenting Language Models (LMs) with structured knowledge graphs (KGs) aims to leverage structured world knowledge to enhance the capability of LMs to complete knowledge-intensive tasks. However, existing methods are unable to effectively utilize the structured knowledge in a KG due to their inability to capture the rich relational semantics of knowledge triplets. Moreover, the modality gap between natural language text and KGs has become a challenging obstacle when aligning and fusing cross-modal information. To address these challenges, we propose a novel knowledge-augmented question answering (QA) model, namely, Graph Reasoning Transformers (GRT). Different from conventional node-level methods, the GRT serves knowledge triplets as atomic knowledge and utilize a triplet-level graph encoder to capture triplet-level graph features. Furthermore, to alleviate the negative effect of the modality gap on joint reasoning, we propose a representation alignment pretraining to align the cross-modal representations and introduce a cross-modal information fusion module with attention bias to enable fine-grained information fusion. Extensive experiments conducted on three knowledge-intensive QA benchmarks show that the GRT outperforms the state-of-the-art KG-augmented QA systems, demonstrating the effectiveness and adaptation of our proposed model.
36
Yu, Donghan, Chenguang Zhu, Yiming Yang, and Michael Zeng. "JAKET: Joint Pre-training of Knowledge Graph and Language Understanding." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (2022): 11630–38. http://dx.doi.org/10.1609/aaai.v36i10.21417.
Texte intégralRésumé :
Knowledge graphs (KGs) contain rich information about world knowledge, entities, and relations. Thus, they can be great supplements to existing pre-trained language models. However, it remains a challenge to efficiently integrate information from KG into language modeling. And the understanding of a knowledge graph requires related context. We propose a novel joint pre-training framework, JAKET, to model both the knowledge graph and language. The knowledge module and language module provide essential information to mutually assist each other: the knowledge module produces embeddings for entities in text while the language module generates context-aware initial embeddings for entities and relations in the graph. Our design enables the pre-trained model to easily adapt to unseen knowledge graphs in new domains. Experiment results on several knowledge-aware NLP tasks show that our proposed framework achieves superior performance by effectively leveraging knowledge in language understanding.
37
Morton, Kenneth, Patrick Wang, Chris Bizon, et al. "ROBOKOP: an abstraction layer and user interface for knowledge graphs to support question answering." Bioinformatics 35, no. 24 (2019): 5382–84. http://dx.doi.org/10.1093/bioinformatics/btz604.
Texte intégralRésumé :
Abstract Summary Knowledge graphs (KGs) are quickly becoming a common-place tool for storing relationships between entities from which higher-level reasoning can be conducted. KGs are typically stored in a graph-database format, and graph-database queries can be used to answer questions of interest that have been posed by users such as biomedical researchers. For simple queries, the inclusion of direct connections in the KG and the storage and analysis of query results are straightforward; however, for complex queries, these capabilities become exponentially more challenging with each increase in complexity of the query. For instance, one relatively complex query can yield a KG with hundreds of thousands of query results. Thus, the ability to efficiently query, store, rank and explore sub-graphs of a complex KG represents a major challenge to any effort designed to exploit the use of KGs for applications in biomedical research and other domains. We present Reasoning Over Biomedical Objects linked in Knowledge Oriented Pathways as an abstraction layer and user interface to more easily query KGs and store, rank and explore query results. Availability and implementation An instance of the ROBOKOP UI for exploration of the ROBOKOP Knowledge Graph can be found at http://robokop.renci.org. The ROBOKOP Knowledge Graph can be accessed at http://robokopkg.renci.org. Code and instructions for building and deploying ROBOKOP are available under the MIT open software license from https://github.com/NCATS-Gamma/robokop. Supplementary information Supplementary data are available at Bioinformatics online.
38
Toroghi, Armin, and Scott Sanner. "Bayesian Inference with Complex Knowledge Graph Evidence." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 18 (2024): 20550–58. http://dx.doi.org/10.1609/aaai.v38i18.30040.
Texte intégralRésumé :
Knowledge Graphs (KGs) provide a widely used format for representing entities and their relationships and have found use in diverse applications including question answering and recommendation. A majority of current research on KG inference has focused on reasoning with atomic facts (triples) and has disregarded the possibility of making complex evidential observations involving logical operators (negation, conjunction, disjunction) and quantifiers (existential, universal). Further, while the application of complex evidence has been explored in KG-based query answering (KGQA) research, in many practical online settings, observations are made sequentially. For example, in KGQA, additional context may be incrementally suggested to narrow down the answer. Or in interactive recommendation, user critiques may be expressed sequentially in order to narrow down a set of preferred items. Both settings are indicative of information filtering or tracking tasks that are reminiscent of belief tracking in Bayesian inference. In fact, in this paper, we precisely cast the problem of belief tracking over unknown KG entities given incremental complex KG evidence as a Bayesian filtering problem. Specifically, we leverage Knowledge-based Model Construction (KBMC) over the logical KG evidence to instantiate a Markov Random Field (MRF) likelihood representation to perform closed-form Bayesian inference with complex KG evidence (BIKG). We experimentally evaluate BIKG in incremental KGQA and interactive recommendation tasks demonstrating that it outperforms non-incremental methodologies and leads to better incorporation of conjunctive evidence vs. existing complex KGQA methods like CQD that leverage fuzzy T-norm operators. Overall, this work demonstrates a novel, efficient, and unified perspective of logic, KGs, and online inference through the lens of closed-form BIKG.
39
Chen, Kai, Guohua Shen, Zhiqiu Huang, and Haijuan Wang. "Improved Entity Linking for Simple Question Answering Over Knowledge Graph." International Journal of Software Engineering and Knowledge Engineering 31, no. 01 (2021): 55–80. http://dx.doi.org/10.1142/s0218194021400039.
Texte intégralRésumé :
Question Answering systems over Knowledge Graphs (KG) answer natural language questions using facts contained in a knowledge graph, and Simple Question Answering over Knowledge Graphs (KG-SimpleQA) means that the question can be answered by a single fact. Entity linking, which is a core component of KG-SimpleQA, detects the entities mentioned in questions, and links them to the actual entity in KG. However, traditional methods ignore some information of entities, especially entity types, which leads to the emergence of entity ambiguity problem. Besides, entity linking suffers from out-of-vocabulary (OOV) problem due to the limitation of pre-trained word embeddings. To address these problems, we encode questions in a novel way and encode the features contained in the entities in a multilevel way. To evaluate the enhancement of the whole KG-SimpleQA brought by our improved entity linking, we utilize a relatively simple approach for relation prediction. Besides, to reduce the impact of losing the feature during the encoding procedure, we utilize a ranking algorithm to re-rank (entity, relation) pairs. According to the experimental results, our method for entity linking achieves an accuracy of 81.8% that beats the state-of-the-art methods, and our improved entity linking brings a boost of 5.6% for the whole KG-SimpleQA.
40
Cheng, Siyuan, Ningyu Zhang, Bozhong Tian, Xi Chen, Qingbin Liu, and Huajun Chen. "Editing Language Model-Based Knowledge Graph Embeddings." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 16 (2024): 17835–43. http://dx.doi.org/10.1609/aaai.v38i16.29737.
Texte intégralRésumé :
Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deployed as static artifacts, making them difficult to modify post-deployment without re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. This task is designed to facilitate rapid, data-efficient updates to KG embeddings without compromising the performance of other aspects. We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hypernetwork to edit/add facts. Our comprehensive experimental results reveal that KGEditor excels in updating specific facts without impacting the overall performance, even when faced with limited training resources. Code and datasets will be available at https://github.com/AnonymousForPapers/DeltaKG.
41
Debruyne, Christophe, Gary Munnelly, Lynn Kilgallon, Declan O’Sullivan, and Peter Crooks. "Creating a Knowledge Graph for Ireland’s Lost History: Knowledge Engineering and Curation in the Beyond 2022 Project." Journal on Computing and Cultural Heritage 15, no. 2 (2022): 1–25. http://dx.doi.org/10.1145/3474829.
Texte intégralRésumé :
The Beyond 2022 project aims to create a virtual archive by digitally reconstructing and digitizing historical records lost in a catastrophic fire which consumed items in the Public Record Office of Ireland in 1922. The project is developing a knowledge graph (KG) to facilitate information retrieval and discovery over the reconstructed items. The project decided to adopt Semantic Web technologies to support its distributed KG and reasoning. In this article, we present our approach to KG generation and management. We elaborate on how we help historians contribute to the KG (via a suite of spreadsheets) and its ontology. We furthermore demonstrate how we use named graphs to store different versions of factoids and their provenance information and how these are serviced in two different endpoints. Modeling data in this manner allows us to acknowledge that history is, to some extent, subjective and different perspectives can exist in parallel. The construction of the KG is driven by competency questions elicited from subject matter experts within the consortium. We avail of CIDOC-CRM as our KG’s foundation, though we needed to extend this ontology with various qualifiers (types) and relations to support the competency questions. We illustrate how one can explore the KG to gain insights and answer questions. We conclude that CIDOC-CRM provides an adequate, albeit complex, foundation for the KG and that named graphs and Linked Data principles are a suitable mechanism to manage sets of factoids and their provenance.
42
Govindapillai, Sini, Lay-Ki Soon, and Su-Cheng Haw. "Resource Description Framework reification for trustworthiness in knowledge graphs." F1000Research 10 (September 2, 2021): 881. http://dx.doi.org/10.12688/f1000research.72843.1.
Texte intégralRésumé :
Knowledge graph (KG) publishes machine-readable representation of knowledge on the Web. Structured data in the knowledge graph is published using Resource Description Framework (RDF) where knowledge is represented as a triple (subject, predicate, object). Due to the presence of erroneous, outdated or conflicting data in the knowledge graph, the quality of facts cannot be guaranteed. Therefore, the provenance of knowledge can assist in building up the trust of these knowledge graphs. In this paper, we have provided an analysis of popular, general knowledge graphs Wikidata and YAGO4 with regard to the representation of provenance and context data. Since RDF does not support metadata for providing provenance and contextualization, an alternate method, RDF reification is employed by most of the knowledge graphs. Trustworthiness of facts in knowledge graph can be enhanced by the addition of metadata like the source of information, location and time of the fact occurrence. Wikidata employs qualifiers to include metadata to facts, while YAGO4 collects metadata from Wikidata qualifiers. RDF reification increases the magnitude of data as several statements are required to represent a single fact. However, facts in Wikidata and YAGO4 can be fetched without using reification. Another limitation for applications that uses provenance data is that not all facts in these knowledge graphs are annotated with provenance data. Structured data in the knowledge graph is noisy. Therefore, the reliability of data in knowledge graphs can be increased by provenance data. To the best of our knowledge, this is the first paper that investigates the method and the extent of the addition of metadata of two prominent KGs, Wikidata and YAGO4.
43
Liu, Xiangyu, Yang Liu, and Wei Hu. "Knowledge Graph Error Detection with Contrastive Confidence Adaption." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 8 (2024): 8824–31. http://dx.doi.org/10.1609/aaai.v38i8.28729.
Texte intégralRésumé :
Knowledge graphs (KGs) often contain various errors. Previous works on detecting errors in KGs mainly rely on triplet embedding from graph structure. We conduct an empirical study and find that these works struggle to discriminate noise from semantically-similar correct triplets. In this paper, we propose a KG error detection model CCA to integrate both textual and graph structural information from triplet reconstruction for better distinguishing semantics. We design interactive contrastive learning to capture the differences between textual and structural patterns. Furthermore, we construct realistic datasets with semantically-similar noise and adversarial noise. Experimental results demonstrate that CCA outperforms state-of-the-art baselines, especially on semantically-similar noise and adversarial noise.
44
Zhang, Zhenyu, Lei Zhang, Dingqi Yang, and Liu Yang. "KRAN: Knowledge Refining Attention Network for Recommendation." ACM Transactions on Knowledge Discovery from Data 16, no. 2 (2022): 1–20. http://dx.doi.org/10.1145/3470783.
Texte intégralRésumé :
Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings.
45
Zeng, Yiping, and Shumin Liu. "Research on recommendation algorithm of Graph attention Network based on Knowledge graph." Journal of Physics: Conference Series 2113, no. 1 (2021): 012085. http://dx.doi.org/10.1088/1742-6596/2113/1/012085.
Texte intégralRésumé :
Abstract The introduction of knowledge graph as the auxiliary information of recommendation system provides a new research idea for personalized intelligent recommendation. However, most of the existing knowledge graph recommendation algorithms fail to effectively solve the problem of unrelated entities, leading to inaccurate prediction of potential preferences of users. To solve this problem, this paper proposes a KG-IGAT model combining knowledge graph and graph attention network, and adds an interest evolution module to graph attention network to capture user interest changes and generate top-N recommendations. Finally, experimental comparison between the proposed model and other algorithms using public data sets shows that KG-IGAT has better recommendation performance.
46
Schwabe, Tim, and Maribel Acosta. "Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks." Proceedings of the ACM on Management of Data 2, no. 1 (2024): 1–26. http://dx.doi.org/10.1145/3639299.
Texte intégralRésumé :
Cardinality Estimation over Knowledge Graphs (KG) is crucial for query optimization, yet remains a challenging task due to the semi-structured nature and complex correlations of data in typical KGs. In this work, we propose GNCE, a novel approach that leverages knowledge graph embeddings and Graph Neural Networks (GNN) to accurately predict the cardinality of conjunctive queries over KGs. GNCE first creates semantically meaningful embeddings for all entities in the KG, which are then used to learn a representation of a query using a GNN to estimate the cardinality of the query. We evaluate GNCE on several KGs in terms of q-Error and demonstrate that it outperforms state-of-the-art approaches based on sampling, summaries, and (machine) learning in terms of estimation accuracy while also having a low execution time and few parameters. Additionally, we show that GNCE performs similarly well on real-world queries and can inductively generalize to unseen entities, making it suitable for use in dynamic query processing scenarios. Our proposed approach has the potential to significantly improve query optimization and related applications that rely on accurate cardinality estimates of conjunctive queries.
47
Yu, Guangya, Qi Ye, and Tong Ruan. "Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label." Bioengineering 11, no. 3 (2024): 225. http://dx.doi.org/10.3390/bioengineering11030225.
Texte intégralRésumé :
The construction of medical knowledge graphs (MKGs) is steadily progressing from manual to automatic methods, which inevitably introduce noise, which could impair the performance of downstream healthcare applications. Existing error detection approaches depend on the topological structure and external labels of entities in MKGs to improve their quality. Nevertheless, due to the cost of manual annotation and imperfect automatic algorithms, precise entity labels in MKGs cannot be readily obtained. To address these issues, we propose an approach named Enhancing error detection on Medical knowledge graphs via intrinsic labEL (EMKGEL). Considering the absence of hyper-view KG, we establish a hyper-view KG and a triplet-level KG for implicit label information and neighborhood information, respectively. Inspired by the success of graph attention networks (GATs), we introduce the hyper-view GAT to incorporate label messages and neighborhood information into representation learning. We leverage a confidence score that combines local and global trustworthiness to estimate the triplets. To validate the effectiveness of our approach, we conducted experiments on three publicly available MKGs, namely PharmKG-8k, DiseaseKG, and DiaKG. Compared with the baseline models, the Precision@K value improved by 0.7%, 6.1%, and 3.6%, respectively, on these datasets. Furthermore, our method empirically showed that it significantly outperformed the baseline on a general knowledge graph, Nell-995.
48
Chen, Liyi, Jie Liu, Yutai Duan, and Runze Wang. "KG-prompt: Interpretable knowledge graph prompt for pre-trained language models." Knowledge-Based Systems 311 (February 2025): 113118. https://doi.org/10.1016/j.knosys.2025.113118.
Texte intégral
49
Yang, Cheng, Chunxia Zhang, and Yihao Chen. "An entity alignment method with attribute augmentation and contrastive learning." Journal of Physics: Conference Series 2858, no. 1 (2024): 012049. http://dx.doi.org/10.1088/1742-6596/2858/1/012049.
Texte intégralRésumé :
Abstract The entity alignment(EA) task is to identify entities with the same semantics in the knowledge graph(KG), an essential issue in KG fusion and big data mining. Existing entity alignment methods mainly adopt graph embedding-based methods. However, they still have some shortcomings. First, they heavily rely on high-quality alignment seed and external semantic information. Secondly, the present attention mechanism focuses on the entire graph information, neglecting the noise of attribute information. This paper proposes an EA approach based on Attribute Augmentation and Contrastive Learning (AACL). Our method introduces attribute augmentation to enhance the structure information of knowledge graphs and reduce dependence on alignment seed. A masked attention mechanism is developed to emphasize important attribute information and mask out invalid attributes to better capture semantic dependencies in the KG. Experimental results on three public datasets indicate that our AACL outperforms the present entity alignment approaches.
50
Torgano, Francesco, Emanuele Cavalleri, Jessica Gliozzo, et al. "RNA Knowledge Graph Analysis via Embedding Methods." WSEAS TRANSACTIONS ON BIOLOGY AND BIOMEDICINE 21 (October 3, 2024): 302–12. http://dx.doi.org/10.37394/23208.2024.21.30.
Texte intégralRésumé :
Recent advances in RNA technologies opened the avenue to the design of novel vaccines as witnessed by the success of the COVID-19 vaccine and also by new ongoing vaccines for cancer. New drugs based on non-coding RNA can also be developed at lower costs considering the relatively simple structure of these molecules with respect to classical recombinant protein technologies. We recently developed RNA-KG, a biomedical Knowledge Graph focused on RNA, collecting information from more than 50 public databases and bio-medical ontologies to support the study of RNA and the design of novel RNA-based drugs. In this work we show that, by applying inductive machine learning methods on top of embedded node and edges obtained by applying classical Graph Representation Learning methods, we can accurately predict the entities and the relationships between entities included in RNA-KG. Our results open the way to the analysis and the discovery of novel relationships between RNAs and other bio-molecules and medical concepts represented in RNA-KG.