To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities...To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.展开更多
Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power system...Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power systems have explored KGs to develop intelligent dispatching systems for increasingly large power grids.With multiple power grid dispatching knowledge graphs(PDKGs)constructed by different agencies,the knowledge fusion of different PDKGs is useful for providing more accurate decision supports.To achieve this,entity alignment that aims at connecting different KGs by identifying equivalent entities is a critical step.Existing entity alignment methods cannot integrate useful structural,attribute,and relational information while calculating entities’similarities and are prone to making many-to-one alignments,thus can hardly achieve the best performance.To address these issues,this paper proposes a collective entity alignment model that integrates three kinds of available information and makes collective counterpart assignments.This model proposes a novel knowledge graph attention network(KGAT)to learn the embeddings of entities and relations explicitly and calculates entities’similarities by adaptively incorporating the structural,attribute,and relational similarities.Then,we formulate the counterpart assignment task as an integer programming(IP)problem to obtain one-to-one alignments.We not only conduct experiments on a pair of PDKGs but also evaluate o ur model on three commonly used cross-lingual KGs.Experimental comparisons indicate that our model outperforms other methods and provides an effective tool for the knowledge fusion of PDKGs.展开更多
Entity alignment(EA)is crucial for knowledge fusion and integration,as it aims to match equivalent entities across different KGs.Recently,many neural-based EA methods have been proposed,focusing on developing various ...Entity alignment(EA)is crucial for knowledge fusion and integration,as it aims to match equivalent entities across different KGs.Recently,many neural-based EA methods have been proposed,focusing on developing various graph representation learning models to match entities in vector spaces.However,most real-world KGs are large-scale and contain rich structural and attribute information about entities,presenting challenges for current approaches designed primarily for small-and medium-sized KGs.To address the challenges of large-scale EA,this paper introduces a simple,effective,and scalable method based on language models.Our approach first leverages the capabilities of language models to encode entities'multi-view information into low-dimensional embeddings,identifying potential aligned entity pairs with high similarity.These candidates are then re-ranked using a global matching algorithm to produce the final alignments.Experimental results show that our method achieves state-of-the-art performance on real-world large-scale EA datasets,with superior accuracy and efficiency compared to existing methods.展开更多
Entity Alignment(EA)aims to identify equivalent entities across different Knowledge Graphs(KGs),enabling knowledge fusion and integration.In recent years,Graph Neural Networks(GNNs)have emerged as a powerful paradigm ...Entity Alignment(EA)aims to identify equivalent entities across different Knowledge Graphs(KGs),enabling knowledge fusion and integration.In recent years,Graph Neural Networks(GNNs)have emerged as a powerful paradigm for EA by leveraging structural information in KGs.However,most existing studies emphasize novel message passing mechanisms while overlooking other crucial GNN design components.This paper presents a comprehensive and systematic evaluation of GNN-based EA methods,focusing on three key aspects:message passing strategies,the number of GNN layers,and the construction of final entity representations.We benchmark a diverse set of GNN models originally developed for tasks such as node classification and knowledge graph completion,and we assess their adaptability to the EA task.Additionally,we explore the effectiveness of skip connection techniques,activation functions,and relational information integration.Our experiments,conducted on standard EA benchmarks including DBP15K and SRPRS,reveal several counterintuitive findings:(1)message passing is indispensable for EA;(2)many node classification GNNs are highly competitive for EA;(3)one or two GNN layers generally achieve optimal performance;and(4)activation functions have minimal impact,while skip connections significantly enhance results.This study provides a principled framework and empirical foundation for designing more effective GNN-based EA models.Code and datasets are publicly available at https://github.com/kg-bnu/GNN-EA.展开更多
Entity Alignment(EA)seeks to identify and match corresponding entities across different Knowledge Graphs(KGs),playing a crucial role in knowledge fusion and integration.Embedding-based entity alignment(EA)has recently...Entity Alignment(EA)seeks to identify and match corresponding entities across different Knowledge Graphs(KGs),playing a crucial role in knowledge fusion and integration.Embedding-based entity alignment(EA)has recently gained considerable attention,resulting in the emergence of many innovative approaches.Initially,these approaches concentrated on learning entity embeddings based on the structural features of knowledge graphs(KGs)as defined by relation triples.Subsequent methods have integrated entities'names and attributes as supplementary information to improve the embeddings used for EA.However,existing methods lack a deep semantic understanding of entity attributes and relations.In this paper,we propose a Large Language Model(LLM)based Entity Alignment method,LLM-Align,which explores the instruction-following and zero-shot capabilities of Large Language Models to infer alignments of entities.LLM-Align uses heuristic methods to select important attributes and relations of entities,and then feeds the selected triples of entities to an LLM to infer the alignment results.To guarantee the quality of alignment results,we design a multi-round voting mechanism to mitigate the hallucination and positional bias issues that occur with LLMs.Experiments on three EA datasets,demonstrating that our approach achieves state-of-the-art performance compared to existing EA methods.展开更多
Entity alignment,which aims to identify entities with the same meaning in different Knowledge Graphs(KGs),is a key step in knowledge integration.Despite the promising results achieved by existing methods,they often fa...Entity alignment,which aims to identify entities with the same meaning in different Knowledge Graphs(KGs),is a key step in knowledge integration.Despite the promising results achieved by existing methods,they often fail to fully leverage the structure information of KGs for entity alignment.Therefore,our goal is to thoroughly explore the features of entity neighbors and relationships to obtain better entity embeddings.In this work,we propose DCEA,an effective dual-context representation learning framework for entity alignment.Specifically,the neighbor-level embedding module introduces relation information to more accurately aggregate neighbor context.The relation-level embedding module utilizes neighbor context to enhance relation-level embeddings.To eliminate semantic gaps between neighbor-level and relation-level embeddings,and fully exploit their complementarity,we design a hybrid embedding fusion model that adaptively performs embedding fusion to obtain powerful joint entity embeddings.We also jointly optimize the contrastive loss of multi-level embeddings,enhancing their mutual reinforcement while preserving the characteristics of neighbor and relation embeddings.Additionally,the decision fusion module combines the similarity scores calculated between entities based on embeddings at different levels to make the final alignment decision.Extensive experimental results on public datasets indicate that our DCEA performs better than state-of-the-art baselines.展开更多
Knowledge graphs(KGs)provide a wealth of prior knowledge for the research on social networks.Crosslingual entity alignment aims at integrating complementary KGs from different languages and thus benefits various knowl...Knowledge graphs(KGs)provide a wealth of prior knowledge for the research on social networks.Crosslingual entity alignment aims at integrating complementary KGs from different languages and thus benefits various knowledge-driven social network studies.Recent entity alignment methods often take an embedding-based approach to model the entity and relation embedding of KGs.However,these studies mostly focus on the information of the entity itself and its structural features but ignore the influence of multiple types of data in KGs.In this paper,we propose a new embedding-based framework named multiview highway graph convolutional network(MHGCN),which considers the entity alignment from the views of entity semantic,relation semantic,and entity attribute.To learn the structural features of an entity,the MHGCN employs a highway graph convolutional network(GCN)for entity embedding in each view.In addition,the MHGCN weights and fuses the multiple views according to the importance of the embedding from each view to obtain a better entity embedding.The alignment entities are identified based on the similarity of entity embeddings.The experimental results show that the MHGCN consistently outperforms the state-of-the-art alignment methods.The research also will benefit knowledge fusion through cross-lingual KG entity alignment.展开更多
Entity alignment(EA)is an important technique aiming to find the same real entity between two different source knowledge graphs(KGs).Current methods typically learn the embedding of entities for EA from the structure ...Entity alignment(EA)is an important technique aiming to find the same real entity between two different source knowledge graphs(KGs).Current methods typically learn the embedding of entities for EA from the structure of KGs for EA.Most EA models are designed for rich-resource languages,requiring sufficient resources such as a parallel corpus and pre-trained language models.However,low-resource language KGs have received less attention,and current models demonstrate poor performance on those low-resource KGs.Recently,researchers have fused relation information and attributes for entity representations to enhance the entity alignment performance,but the relation semantics are often ignored.To address these issues,we propose a novel Semantic-aware Graph Neural Network(SGNN)for entity alignment.First,we generate pseudo sentences according to the relation triples and produce representations using pre-trained models.Second,our approach explores semantic information from the connected relations by a graph neural network.Our model captures expanded feature information from KGs.Experimental results using three low-resource languages demonstrate that our proposed SGNN approach out performs better than state-of-the-art alignment methods on three proposed datasets and three public datasets.展开更多
Biomedical entity alignment,composed of two subtasks:entity identification and entity-concept mapping,is of great research value in biomedical text mining while these techniques are widely used for name entity standar...Biomedical entity alignment,composed of two subtasks:entity identification and entity-concept mapping,is of great research value in biomedical text mining while these techniques are widely used for name entity standardization,information retrieval,knowledge acquisition and ontology construc-tion.Previous works made many efforts on feature engineering to employ feature-based models for entity identification and alignment.However,the models depended on subjective feature selection may suffer error propagation and are not able to uti-lize the hidden information.With rapid development in health-related research,researchers need an effective method to explore the large amount of available biomedical literatures.Therefore,we propose a two-stage entity alignment process,biomedical entity exploring model,to identify biomedical entities and align them to the knowledge base interactively.The model aims to automatically obtain semantic information for extracting biomedical entities and mining semantic relations through the standard biomedical knowledge base.The experiments show that the proposed method achieves better performance on entity alignment.The proposed model dramatically improves the FI scores of the task by about 4.5%in entity identification and 2.5%in entity-concept mapping.展开更多
The means of knowledge graph embedding is to transform entities and relations into low-dimensional vectors.When it is necessary to obtain the embedding results of two hetero-field knowledge graphs in a unified vector ...The means of knowledge graph embedding is to transform entities and relations into low-dimensional vectors.When it is necessary to obtain the embedding results of two hetero-field knowledge graphs in a unified vector space,there are only a few aligned entities between them,previous methods first need to merge the two graphs into a large graph,and then re-embed the entire large graph.This ignores the potential reuse of the original representation embeddings of two knowledge graphs and will lead to a lot of time consumption.To address this problem,this paper proposes a hetero-field knowledge graph embedding fusion model(BlockEF)based on aligned entities.According to the fact that the aligned entities of the two graphs should be located in the same position in the vector space,the transformation relationship between the embeddings of two graphs is firstly obtained,and then graph embedding is fine-tuned and optimized to achieve efficient fusion of hetero-field knowledge graph embeddings.The experimental results show that our method can significantly reduce the computational burden of heterofield knowledge graph embedding fusion and ensure the quality of embedding fusion.展开更多
基金partially supported by the National Natural Science Foundation of China under Grants 62471493 and 62402257(for conceptualization and investigation)partially supported by the Natural Science Foundation of Shandong Province,China under Grants ZR2023LZH017,ZR2024MF066,and 2023QF025(for formal analysis and validation)+1 种基金partially supported by the Open Foundation of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)under Grant 2023ZD010(for methodology and model design)partially supported by the Russian Science Foundation(RSF)Project under Grant 22-71-10095-P(for validation and results verification).
文摘To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.
基金supported by the National Key R&D Program of China(2018AAA0101502)the Science and Technology Project of SGCC(State Grid Corporation of China):Fundamental Theory of Human-in-the-Loop Hybrid-Augmented Intelligence for Power Grid Dispatch and Control。
文摘Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power systems have explored KGs to develop intelligent dispatching systems for increasingly large power grids.With multiple power grid dispatching knowledge graphs(PDKGs)constructed by different agencies,the knowledge fusion of different PDKGs is useful for providing more accurate decision supports.To achieve this,entity alignment that aims at connecting different KGs by identifying equivalent entities is a critical step.Existing entity alignment methods cannot integrate useful structural,attribute,and relational information while calculating entities’similarities and are prone to making many-to-one alignments,thus can hardly achieve the best performance.To address these issues,this paper proposes a collective entity alignment model that integrates three kinds of available information and makes collective counterpart assignments.This model proposes a novel knowledge graph attention network(KGAT)to learn the embeddings of entities and relations explicitly and calculates entities’similarities by adaptively incorporating the structural,attribute,and relational similarities.Then,we formulate the counterpart assignment task as an integer programming(IP)problem to obtain one-to-one alignments.We not only conduct experiments on a pair of PDKGs but also evaluate o ur model on three commonly used cross-lingual KGs.Experimental comparisons indicate that our model outperforms other methods and provides an effective tool for the knowledge fusion of PDKGs.
基金supported by the National Natural Science Foundation of China(No.62276026)。
文摘Entity alignment(EA)is crucial for knowledge fusion and integration,as it aims to match equivalent entities across different KGs.Recently,many neural-based EA methods have been proposed,focusing on developing various graph representation learning models to match entities in vector spaces.However,most real-world KGs are large-scale and contain rich structural and attribute information about entities,presenting challenges for current approaches designed primarily for small-and medium-sized KGs.To address the challenges of large-scale EA,this paper introduces a simple,effective,and scalable method based on language models.Our approach first leverages the capabilities of language models to encode entities'multi-view information into low-dimensional embeddings,identifying potential aligned entity pairs with high similarity.These candidates are then re-ranked using a global matching algorithm to produce the final alignments.Experimental results show that our method achieves state-of-the-art performance on real-world large-scale EA datasets,with superior accuracy and efficiency compared to existing methods.
基金supported by the National Natural Science Foundation of China(No.62276026)。
文摘Entity Alignment(EA)aims to identify equivalent entities across different Knowledge Graphs(KGs),enabling knowledge fusion and integration.In recent years,Graph Neural Networks(GNNs)have emerged as a powerful paradigm for EA by leveraging structural information in KGs.However,most existing studies emphasize novel message passing mechanisms while overlooking other crucial GNN design components.This paper presents a comprehensive and systematic evaluation of GNN-based EA methods,focusing on three key aspects:message passing strategies,the number of GNN layers,and the construction of final entity representations.We benchmark a diverse set of GNN models originally developed for tasks such as node classification and knowledge graph completion,and we assess their adaptability to the EA task.Additionally,we explore the effectiveness of skip connection techniques,activation functions,and relational information integration.Our experiments,conducted on standard EA benchmarks including DBP15K and SRPRS,reveal several counterintuitive findings:(1)message passing is indispensable for EA;(2)many node classification GNNs are highly competitive for EA;(3)one or two GNN layers generally achieve optimal performance;and(4)activation functions have minimal impact,while skip connections significantly enhance results.This study provides a principled framework and empirical foundation for designing more effective GNN-based EA models.Code and datasets are publicly available at https://github.com/kg-bnu/GNN-EA.
基金supported by the National Natural Science Foundation of China(No.62276026)。
文摘Entity Alignment(EA)seeks to identify and match corresponding entities across different Knowledge Graphs(KGs),playing a crucial role in knowledge fusion and integration.Embedding-based entity alignment(EA)has recently gained considerable attention,resulting in the emergence of many innovative approaches.Initially,these approaches concentrated on learning entity embeddings based on the structural features of knowledge graphs(KGs)as defined by relation triples.Subsequent methods have integrated entities'names and attributes as supplementary information to improve the embeddings used for EA.However,existing methods lack a deep semantic understanding of entity attributes and relations.In this paper,we propose a Large Language Model(LLM)based Entity Alignment method,LLM-Align,which explores the instruction-following and zero-shot capabilities of Large Language Models to infer alignments of entities.LLM-Align uses heuristic methods to select important attributes and relations of entities,and then feeds the selected triples of entities to an LLM to infer the alignment results.To guarantee the quality of alignment results,we design a multi-round voting mechanism to mitigate the hallucination and positional bias issues that occur with LLMs.Experiments on three EA datasets,demonstrating that our approach achieves state-of-the-art performance compared to existing EA methods.
基金supported by the“pioneer”and“Leading Goose”Key R&D Program of Zhejiang Province under Grant No.2022C03106the Zhejiang Provincial Natural Science Foundation of China under Grant No.LY23F020010the National Natural Science Foundation of China under Grant No.62077015.
文摘Entity alignment,which aims to identify entities with the same meaning in different Knowledge Graphs(KGs),is a key step in knowledge integration.Despite the promising results achieved by existing methods,they often fail to fully leverage the structure information of KGs for entity alignment.Therefore,our goal is to thoroughly explore the features of entity neighbors and relationships to obtain better entity embeddings.In this work,we propose DCEA,an effective dual-context representation learning framework for entity alignment.Specifically,the neighbor-level embedding module introduces relation information to more accurately aggregate neighbor context.The relation-level embedding module utilizes neighbor context to enhance relation-level embeddings.To eliminate semantic gaps between neighbor-level and relation-level embeddings,and fully exploit their complementarity,we design a hybrid embedding fusion model that adaptively performs embedding fusion to obtain powerful joint entity embeddings.We also jointly optimize the contrastive loss of multi-level embeddings,enhancing their mutual reinforcement while preserving the characteristics of neighbor and relation embeddings.Additionally,the decision fusion module combines the similarity scores calculated between entities based on embeddings at different levels to make the final alignment decision.Extensive experimental results on public datasets indicate that our DCEA performs better than state-of-the-art baselines.
基金supported by the National Natural Science Foundation of China(No.61873288)Research on Key Technologies and Application for the Time Series Data of State Grid Hunan Electirc Power Company(No.5216A00036)+1 种基金the Hunan Key Laboratory for Internet of Things in Electricity(No.2019TP1016)CAAI-Huawei Mind Spore Open Fund。
文摘Knowledge graphs(KGs)provide a wealth of prior knowledge for the research on social networks.Crosslingual entity alignment aims at integrating complementary KGs from different languages and thus benefits various knowledge-driven social network studies.Recent entity alignment methods often take an embedding-based approach to model the entity and relation embedding of KGs.However,these studies mostly focus on the information of the entity itself and its structural features but ignore the influence of multiple types of data in KGs.In this paper,we propose a new embedding-based framework named multiview highway graph convolutional network(MHGCN),which considers the entity alignment from the views of entity semantic,relation semantic,and entity attribute.To learn the structural features of an entity,the MHGCN employs a highway graph convolutional network(GCN)for entity embedding in each view.In addition,the MHGCN weights and fuses the multiple views according to the importance of the embedding from each view to obtain a better entity embedding.The alignment entities are identified based on the similarity of entity embeddings.The experimental results show that the MHGCN consistently outperforms the state-of-the-art alignment methods.The research also will benefit knowledge fusion through cross-lingual KG entity alignment.
基金National Natural Science Foundation of China(Nos.U21B2027,61972186,61732005)Major Science and Technology Projects of Yunnan Province(Nos.202202AD080003,202203AA080004).
文摘Entity alignment(EA)is an important technique aiming to find the same real entity between two different source knowledge graphs(KGs).Current methods typically learn the embedding of entities for EA from the structure of KGs for EA.Most EA models are designed for rich-resource languages,requiring sufficient resources such as a parallel corpus and pre-trained language models.However,low-resource language KGs have received less attention,and current models demonstrate poor performance on those low-resource KGs.Recently,researchers have fused relation information and attributes for entity representations to enhance the entity alignment performance,but the relation semantics are often ignored.To address these issues,we propose a novel Semantic-aware Graph Neural Network(SGNN)for entity alignment.First,we generate pseudo sentences according to the relation triples and produce representations using pre-trained models.Second,our approach explores semantic information from the connected relations by a graph neural network.Our model captures expanded feature information from KGs.Experimental results using three low-resource languages demonstrate that our proposed SGNN approach out performs better than state-of-the-art alignment methods on three proposed datasets and three public datasets.
基金supported by the National Key Research and Development Program of China(2018YFB1003404)the National Natural Science Foundation of China(Grant Nos.61672142,61402213)+1 种基金the Fundamental Research Funds for the Central Universities(N150408001-3,N150404013)Natural Science Foundation of Liaoning Province(20170540471)。
文摘Biomedical entity alignment,composed of two subtasks:entity identification and entity-concept mapping,is of great research value in biomedical text mining while these techniques are widely used for name entity standardization,information retrieval,knowledge acquisition and ontology construc-tion.Previous works made many efforts on feature engineering to employ feature-based models for entity identification and alignment.However,the models depended on subjective feature selection may suffer error propagation and are not able to uti-lize the hidden information.With rapid development in health-related research,researchers need an effective method to explore the large amount of available biomedical literatures.Therefore,we propose a two-stage entity alignment process,biomedical entity exploring model,to identify biomedical entities and align them to the knowledge base interactively.The model aims to automatically obtain semantic information for extracting biomedical entities and mining semantic relations through the standard biomedical knowledge base.The experiments show that the proposed method achieves better performance on entity alignment.The proposed model dramatically improves the FI scores of the task by about 4.5%in entity identification and 2.5%in entity-concept mapping.
基金supported by the Deep-time Digital Earth (DDE) Big Science Programin part by the National Natural Science Foundation of China (NSFC) (No. 61972365)in part by the Open Research Project of the Hubei Key Laboratory of Intelligent Geo-Information Processing (No. KLIGIP-2021B01)
文摘The means of knowledge graph embedding is to transform entities and relations into low-dimensional vectors.When it is necessary to obtain the embedding results of two hetero-field knowledge graphs in a unified vector space,there are only a few aligned entities between them,previous methods first need to merge the two graphs into a large graph,and then re-embed the entire large graph.This ignores the potential reuse of the original representation embeddings of two knowledge graphs and will lead to a lot of time consumption.To address this problem,this paper proposes a hetero-field knowledge graph embedding fusion model(BlockEF)based on aligned entities.According to the fact that the aligned entities of the two graphs should be located in the same position in the vector space,the transformation relationship between the embeddings of two graphs is firstly obtained,and then graph embedding is fine-tuned and optimized to achieve efficient fusion of hetero-field knowledge graph embeddings.The experimental results show that our method can significantly reduce the computational burden of heterofield knowledge graph embedding fusion and ensure the quality of embedding fusion.
