The objective of knowledge graph completion is to comprehend the structure and inherent relationships of domain knowledge,thereby providing a valuable foundation for knowledge reasoning and analysis.However,existing m...The objective of knowledge graph completion is to comprehend the structure and inherent relationships of domain knowledge,thereby providing a valuable foundation for knowledge reasoning and analysis.However,existing methods for knowledge graph completion face challenges.For instance,rule-based completion methods exhibit high accuracy and interpretability,but encounter difficulties when handling large knowledge graphs.In contrast,embedding-based completion methods demonstrate strong scalability and efficiency,but also have limited utilisation of domain knowledge.In response to the aforementioned issues,we propose a method of pre-training and inference for knowledge graph completion based on integrated rules.The approach combines rule mining and reasoning to generate precise candidate facts.Subsequently,a pre-trained language model is fine-tuned and probabilistic structural loss is incorporated to embed the knowledge graph.This enables the language model to capture more deep semantic information while the loss function reconstructs the structure of the knowledge graph.This enables the language model to capture more deep semantic information while the loss function reconstructs the structure of the knowledge graph.Extensive tests using various publicly accessible datasets have indicated that the suggested model performs better than current techniques in tackling knowledge graph completion problems.展开更多
In the field of discretization-based meshfree/meshless methods,the improvements in the higher-order consistency,stability,and computational efficiency are of great concerns in computational science and numerical solut...In the field of discretization-based meshfree/meshless methods,the improvements in the higher-order consistency,stability,and computational efficiency are of great concerns in computational science and numerical solutions to partial differential equations.Various alternative numerical methods of the finite particle method(FPM)frame have been extended from mathematical theories to numerical applications separately.As a comprehensive numerical scheme,this study suggests a unified resolved program for numerically investigating their accuracy,stability,consistency,computational efficiency,and practical applicability in industrial engineering contexts.The high-order finite particle method(HFPM)and corrected methods based on the multivariate Taylor series expansion are constructed and analyzed to investigate the whole applicability in different benchmarks of computational fluid dynamics.Specifically,four benchmarks are designed purposefully from statical exact solutions to multifaceted hydrodynamic tests,which possess different numerical performances on the particle consistency,numerical discretized forms,particle distributions,and transient time evolutional stabilities.This study offers a numerical reference for the current unified resolved program.展开更多
Despite the large number of certificateless encryption schemes proposed recently, many of them have been found insecure under a practical attack, called malicious-but-passive KGC （Key Generation Center） attack. In t...Despite the large number of certificateless encryption schemes proposed recently, many of them have been found insecure under a practical attack, called malicious-but-passive KGC （Key Generation Center） attack. In this work we propose the first generic construction of certificateless encryption, which can be proven secure against malicious-but- passive KGC attacks in the standard model. In order to encrypt a message of any length, we consider the KEM/DEM （key encapsulation mechanism/data encapsulation mechanism） framework in the certificateless setting, and propose a generic construction of certificateless key encapsulation mechanism （CL-KEM） secure against malicious-but-passive KGC attacks in the standard model. It is based on an identity-based KEM, a public key encryption and a message authentication code. The high efficiency of our construction is due to the efficient implementations of these underlying building blocks, and is comparable to Bentahar et al.＇s CL-KEMs, which have only been proven secure under the random oracle model with no consideration of the malicious-but-passive KGC attack. We also introduce the notion of certificateless tag-based KEM （CL-TKEM）, which is an extension of Abe et al.＇s work to the certificateless setting. We show that an efficient CL-TKEM can be constructed by modifying our CL-KEM scheme. We also show that with a CL-TKEM and a data encapsulation mechanism secure under our proposed security model, an efficient certificateless hybrid encryption can be constructed by applying Abe et al.＇s transformation in the certificateless setting.展开更多
Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the k...Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the knowledge graph increases exponentially with the depth of the tree,whereas the distances of nodes in Euclidean space are second-order polynomial distances,whereby knowledge embedding using graph neural networks in Euclidean space will not represent the distances between nodes well.This paper introduces a novel approach called hyperbolic hierarchical graph attention network(H2GAT)to rectify this limitation.Firstly,the paper conducts knowledge representation in the hyperbolic space,effectively mitigating the issue of exponential growth of nodes with tree depth and consequent information loss.Secondly,it introduces a hierarchical graph atten-tion mechanism specifically designed for the hyperbolic space,allowing for enhanced capture of the network structure inherent in the knowledge graph.Finally,the efficacy of the proposed H2GAT model is evaluated on benchmark datasets,namely WN18RR and FB15K-237,thereby validating its effectiveness.The H2GAT model achieved 0.445,0.515,and 0.586 in the Hits@1,Hits@3 and Hits@10 metrics respectively on the WN18RR dataset and 0.243,0.367 and 0.518 on the FB15K-237 dataset.By incorporating hyperbolic space embedding and hierarchical graph attention,the H2GAT model successfully addresses the limitations of existing hyperbolic knowledge embedding models,exhibiting its competence in knowledge graph completion tasks.展开更多
基金supported by the Sichuan Science and Technology Program(No.2024YFHZ0024)the National Natural Science Foundation of China(No.62276215)。
文摘The objective of knowledge graph completion is to comprehend the structure and inherent relationships of domain knowledge,thereby providing a valuable foundation for knowledge reasoning and analysis.However,existing methods for knowledge graph completion face challenges.For instance,rule-based completion methods exhibit high accuracy and interpretability,but encounter difficulties when handling large knowledge graphs.In contrast,embedding-based completion methods demonstrate strong scalability and efficiency,but also have limited utilisation of domain knowledge.In response to the aforementioned issues,we propose a method of pre-training and inference for knowledge graph completion based on integrated rules.The approach combines rule mining and reasoning to generate precise candidate facts.Subsequently,a pre-trained language model is fine-tuned and probabilistic structural loss is incorporated to embed the knowledge graph.This enables the language model to capture more deep semantic information while the loss function reconstructs the structure of the knowledge graph.This enables the language model to capture more deep semantic information while the loss function reconstructs the structure of the knowledge graph.Extensive tests using various publicly accessible datasets have indicated that the suggested model performs better than current techniques in tackling knowledge graph completion problems.
基金supported by the National Natural Science Foundation of China(No.12002290)。
文摘In the field of discretization-based meshfree/meshless methods,the improvements in the higher-order consistency,stability,and computational efficiency are of great concerns in computational science and numerical solutions to partial differential equations.Various alternative numerical methods of the finite particle method(FPM)frame have been extended from mathematical theories to numerical applications separately.As a comprehensive numerical scheme,this study suggests a unified resolved program for numerically investigating their accuracy,stability,consistency,computational efficiency,and practical applicability in industrial engineering contexts.The high-order finite particle method(HFPM)and corrected methods based on the multivariate Taylor series expansion are constructed and analyzed to investigate the whole applicability in different benchmarks of computational fluid dynamics.Specifically,four benchmarks are designed purposefully from statical exact solutions to multifaceted hydrodynamic tests,which possess different numerical performances on the particle consistency,numerical discretized forms,particle distributions,and transient time evolutional stabilities.This study offers a numerical reference for the current unified resolved program.
文摘Despite the large number of certificateless encryption schemes proposed recently, many of them have been found insecure under a practical attack, called malicious-but-passive KGC （Key Generation Center） attack. In this work we propose the first generic construction of certificateless encryption, which can be proven secure against malicious-but- passive KGC attacks in the standard model. In order to encrypt a message of any length, we consider the KEM/DEM （key encapsulation mechanism/data encapsulation mechanism） framework in the certificateless setting, and propose a generic construction of certificateless key encapsulation mechanism （CL-KEM） secure against malicious-but-passive KGC attacks in the standard model. It is based on an identity-based KEM, a public key encryption and a message authentication code. The high efficiency of our construction is due to the efficient implementations of these underlying building blocks, and is comparable to Bentahar et al.＇s CL-KEMs, which have only been proven secure under the random oracle model with no consideration of the malicious-but-passive KGC attack. We also introduce the notion of certificateless tag-based KEM （CL-TKEM）, which is an extension of Abe et al.＇s work to the certificateless setting. We show that an efficient CL-TKEM can be constructed by modifying our CL-KEM scheme. We also show that with a CL-TKEM and a data encapsulation mechanism secure under our proposed security model, an efficient certificateless hybrid encryption can be constructed by applying Abe et al.＇s transformation in the certificateless setting.
基金the Beijing Municipal Science and Technology Program(No.Z231100001323004).
文摘Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the knowledge graph increases exponentially with the depth of the tree,whereas the distances of nodes in Euclidean space are second-order polynomial distances,whereby knowledge embedding using graph neural networks in Euclidean space will not represent the distances between nodes well.This paper introduces a novel approach called hyperbolic hierarchical graph attention network(H2GAT)to rectify this limitation.Firstly,the paper conducts knowledge representation in the hyperbolic space,effectively mitigating the issue of exponential growth of nodes with tree depth and consequent information loss.Secondly,it introduces a hierarchical graph atten-tion mechanism specifically designed for the hyperbolic space,allowing for enhanced capture of the network structure inherent in the knowledge graph.Finally,the efficacy of the proposed H2GAT model is evaluated on benchmark datasets,namely WN18RR and FB15K-237,thereby validating its effectiveness.The H2GAT model achieved 0.445,0.515,and 0.586 in the Hits@1,Hits@3 and Hits@10 metrics respectively on the WN18RR dataset and 0.243,0.367 and 0.518 on the FB15K-237 dataset.By incorporating hyperbolic space embedding and hierarchical graph attention,the H2GAT model successfully addresses the limitations of existing hyperbolic knowledge embedding models,exhibiting its competence in knowledge graph completion tasks.
