Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowled...Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowledge graph reasoning is more challenging due to its temporal nature.In essence,within each time step in a dynamic knowledge graph,there exists structural dependencies among entities and relations,whereas between adjacent time steps,there exists temporal continuity.Based on these structural and temporal characteristics,we propose a model named“DKGR-DR”to learn distributed representations of entities and relations by combining recurrent neural networks and graph neural networks to capture structural dependencies and temporal continuity in DKGs.In addition,we construct a static attribute graph to represent entities’inherent properties.DKGR-DR is capable of modeling both dynamic and static aspects of entities,enabling effective entity prediction and relation prediction.We conduct experiments on ICEWS05-15,ICEWS18,and ICEWS14 to demonstrate that DKGR-DR achieves competitive performance.展开更多
Pixel-wise segmentation techniques based on deep learning have been widely applied in the inspection of product surface defects to ensure product quality.However,existing models based on deep learning primarily focus ...Pixel-wise segmentation techniques based on deep learning have been widely applied in the inspection of product surface defects to ensure product quality.However,existing models based on deep learning primarily focus on separate specific defect types,which introduces challenges in generalizing them to the detection of diverse product defects.The relatively low occurrence probability of certain defects also sets obstacles in obtaining sufficient defect samples for effective model training.Herein,an innovative dual-branch edge-based graph reasoning network(DEGRNet)is demonstrated for the few-shot segmentation(FSS)of industrial surface defects,which can be easily generalized to various defects with minimal labeled defect samples.DEGRNet mainly consists of a background eliminating(BE)module,an edge reinforcement(ER)module,and a graph reasoning module.The BE module can effectively fuse the feature information from the support image and support mask to reduce background interference,while the ER module works to accurately extract edge contour information.The rough segmentation maps from BE and the boundary-enhanced segmentation maps from ER are simultaneously input into the dual-branch graph reasoning module to enhance the modeling capability of long-distance feature information and refine segmentation boundaries.This feature enables our model to fully utilize global image features and gain robust generalization capabilities for unknown defect types.The results of multiple experiments validate the effectiveness of the asproposed modules.Our model achieves state-of-the-art performance metrics in few-shot defect segmentations.Specifically,our model exhibits 2.61% and 3.50% improvements in mean intersection over union under the-shot and-shot conditions,respectively,compared with existing state-of-the-art FSS models.展开更多
Extrapolation on Temporal Knowledge Graphs(TKGs)aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order.The temporally adjacent facts in TKGs naturally form event sequences,ca...Extrapolation on Temporal Knowledge Graphs(TKGs)aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order.The temporally adjacent facts in TKGs naturally form event sequences,called event evolution patterns,implying informative temporal dependencies between events.Recently,many extrapolation works on TKGs have been devoted to modelling these evolutional patterns,but the task is still far from resolved because most existing works simply rely on encoding these patterns into entity representations while overlooking the significant information implied by relations of evolutional patterns.However,the authors realise that the temporal dependencies inherent in the relations of these event evolution patterns may guide the follow-up event prediction to some extent.To this end,a Temporal Relational Context-based Temporal Dependencies Learning Network(TRenD)is proposed to explore the temporal context of relations for more comprehensive learning of event evolution patterns,especially those temporal dependencies caused by interactive patterns of relations.Trend incorporates a semantic context unit to capture semantic correlations between relations,and a structural context unit to learn the interaction pattern of relations.By learning the temporal contexts of relations semantically and structurally,the authors gain insights into the underlying event evolution patterns,enabling to extract comprehensive historical information for future prediction better.Experimental results on benchmark datasets demonstrate the superiority of the model.展开更多
The rapid advancement of information technologies has significantly intensified the focus on cyberspace security across various sectors.In this evolving landscape,attackers deploy many techniques-including exploits,we...The rapid advancement of information technologies has significantly intensified the focus on cyberspace security across various sectors.In this evolving landscape,attackers deploy many techniques-including exploits,weakness identification,and complex multi-step attacks-to gain unauthorized access to systems.Conversely,defenders harness insights from a variety of sources to pinpoint potential threats.Prominent public cybersecurity databases such as the Adversarial Tactics,Techniques,and Common Knowledge(ATT&CK),Common Attack Pattern Enumeration and Classification(CAPEC),Common Vulnerabilities and Exposures(CVE),Common Weakness Enumeration(CWE),and Common Platform Enumeration(CPE)provide extensive data on security entities and their interrelations,playing a pivotal role in enriching the understanding of cybersecurity challenges and assisting in comprehensive defensive analyses.However,the semantic cross-analysis of these databases,crucial for identifying obscure threat patterns,remains underexploited.In this study,we amalgamate data from these disparate sources into a cohesive threat knowledge graph and introduce a novel knowledge representation learning approach,A4CKGE(ATT&CKCAPEC-CWE-CVE-CPE Knowledge Graph Embedding).This method utilizes advanced structural and textual analytics to predict interactions among security entities such as products,vulnerabilities,weaknesses,and multi-step attack sequences,employing complex attack templates generated through a Large Language Model(LLM).Our extensive experiments demonstrate that this approach significantly outperforms existing state-of-the-art methods in effectively predicting these relationships.The findings validate the efficacy of our threat knowledge graph in unveiling hidden connections,thereby highlighting its potential to strengthen cybersecurity defenses substantially.展开更多
Proactive dialogue generates dialogue utterance based on a conversation goal and a given knowledge graph(KG). Existing methods combine knowledge of each turn of dialogue with knowledge triples by hidden variables, res...Proactive dialogue generates dialogue utterance based on a conversation goal and a given knowledge graph(KG). Existing methods combine knowledge of each turn of dialogue with knowledge triples by hidden variables, resulting in the interpretability of generation results is relatively poor. An interpretable knowledge-aware path(KAP) model was proposed for knowledge reasoning in proactive dialogue generation.KAP model can transform explicit and implicit knowledge of each turn of dialogue into corresponding dialogue state matrix, thus forming the KAP for dialogue history. Based on KAP, the next turn of dialogue state vector can be infered from both the topology and semantic of KG. This vector can indicate knowledge distribution of next sentence, so it enhances the accuracy and interpretability of dialogue generation. Experiments show that KAP model’s dialogue generation is closer to actual conversation than other state-of-the-art proactive dialogue models.展开更多
Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent performance.Reinforcement Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential ...Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent performance.Reinforcement Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential decision problem.An intractable shortcoming of multi-hop reasoning with RL is that sparse reward signals make performance unstable.Current mainstream methods apply heuristic reward functions to counter this challenge.However,the inaccurate rewards caused by heuristic functions guide the agent to improper inference paths and unrelated object entities.To this end,we propose a novel adaptive Inverse Reinforcement Learning(IRL)framework for multi-hop reasoning,called AInvR.(1)To counter the missing and spurious paths,we replace the heuristic rule rewards with an adaptive rule reward learning mechanism based on agent’s inference trajectories;(2)to alleviate the impact of over-rewarded object entities misled by inaccurate reward shaping and rules,we propose an adaptive negative hit reward learning mechanism based on agent’s sampling strategy;(3)to further explore diverse paths and mitigate the influence of missing facts,we design a reward dropout mechanism to randomly mask and perturb reward parameters for the reward learning process.Experimental results on several benchmark knowledge graphs demonstrate that our method is more effective than existing multi-hop approaches.展开更多
Cross-document relation extraction(RE),as an extension of information extraction,requires integrating information from multiple documents retrieved from open domains with a large number of irrelevant or confusing nois...Cross-document relation extraction(RE),as an extension of information extraction,requires integrating information from multiple documents retrieved from open domains with a large number of irrelevant or confusing noisy texts.Previous studies focus on the attention mechanism to construct the connection between different text features through semantic similarity.However,similarity-based methods cannot distinguish valid information from highly similar retrieved documents well.How to design an effective algorithm to implement aggregated reasoning in confusing information with similar features still remains an open issue.To address this problem,we design a novel local-toglobal causal reasoning(LGCR)network for cross-document RE,which enables efficient distinguishing,filtering and global reasoning on complex information from a causal perspective.Specifically,we propose a local causal estimation algorithm to estimate the causal effect,which is the first trial to use the causal reasoning independent of feature similarity to distinguish between confusing and valid information in cross-document RE.Furthermore,based on the causal effect,we propose a causality guided global reasoning algorithm to filter the confusing information and achieve global reasoning.Experimental results under the closed and the open settings of the large-scale dataset Cod RED demonstrate our LGCR network significantly outperforms the state-ofthe-art methods and validate the effectiveness of causal reasoning in confusing information processing.展开更多
In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring mi...In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.展开更多
It is desired to obtain the joint probability distribution(JPD) over a set of random variables with local data, so as to avoid the hard work to collect statistical data in the scale of all variables. A lot of work has...It is desired to obtain the joint probability distribution(JPD) over a set of random variables with local data, so as to avoid the hard work to collect statistical data in the scale of all variables. A lot of work has been done when all variables are in a known directed acyclic graph(DAG). However, steady directed cyclic graphs(DCGs) may be involved when we simply combine modules containing local data together, where a module is composed of a child variable and its parent variables. So far, the physical and statistical meaning of steady DCGs remain unclear and unsolved. This paper illustrates the physical and statistical meaning of steady DCGs, and presents a method to calculate the JPD with local data, given that all variables are in a known single-valued Dynamic Uncertain Causality Graph(S-DUCG), and thus defines a new Bayesian Network with steady DCGs. The so-called single-valued means that only the causes of the true state of a variable are specified, while the false state is the complement of the true state.展开更多
基金supported byNationalNatural Science Foundation of China(GrantNos.62071098,U24B20128)Sichuan Science and Technology Program(Grant No.2022YFG0319).
文摘Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowledge graph reasoning is more challenging due to its temporal nature.In essence,within each time step in a dynamic knowledge graph,there exists structural dependencies among entities and relations,whereas between adjacent time steps,there exists temporal continuity.Based on these structural and temporal characteristics,we propose a model named“DKGR-DR”to learn distributed representations of entities and relations by combining recurrent neural networks and graph neural networks to capture structural dependencies and temporal continuity in DKGs.In addition,we construct a static attribute graph to represent entities’inherent properties.DKGR-DR is capable of modeling both dynamic and static aspects of entities,enabling effective entity prediction and relation prediction.We conduct experiments on ICEWS05-15,ICEWS18,and ICEWS14 to demonstrate that DKGR-DR achieves competitive performance.
基金the projects supported by the National Natural Science Foundation of China(Grant No.52305623)Natural Science Foundation of Wuhan,China(Grant No.2024040801020282)Fundamental Research Funds for the Central Universities,China University of Geosciences(Wuhan)(Grant No.120-162301212389).
文摘Pixel-wise segmentation techniques based on deep learning have been widely applied in the inspection of product surface defects to ensure product quality.However,existing models based on deep learning primarily focus on separate specific defect types,which introduces challenges in generalizing them to the detection of diverse product defects.The relatively low occurrence probability of certain defects also sets obstacles in obtaining sufficient defect samples for effective model training.Herein,an innovative dual-branch edge-based graph reasoning network(DEGRNet)is demonstrated for the few-shot segmentation(FSS)of industrial surface defects,which can be easily generalized to various defects with minimal labeled defect samples.DEGRNet mainly consists of a background eliminating(BE)module,an edge reinforcement(ER)module,and a graph reasoning module.The BE module can effectively fuse the feature information from the support image and support mask to reduce background interference,while the ER module works to accurately extract edge contour information.The rough segmentation maps from BE and the boundary-enhanced segmentation maps from ER are simultaneously input into the dual-branch graph reasoning module to enhance the modeling capability of long-distance feature information and refine segmentation boundaries.This feature enables our model to fully utilize global image features and gain robust generalization capabilities for unknown defect types.The results of multiple experiments validate the effectiveness of the asproposed modules.Our model achieves state-of-the-art performance metrics in few-shot defect segmentations.Specifically,our model exhibits 2.61% and 3.50% improvements in mean intersection over union under the-shot and-shot conditions,respectively,compared with existing state-of-the-art FSS models.
基金supported in part by the National Natural Science Foundation of China(No.62302507)and the funding of Harbin Institute of Technology(Shenzhen)(No.20210035).
文摘Extrapolation on Temporal Knowledge Graphs(TKGs)aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order.The temporally adjacent facts in TKGs naturally form event sequences,called event evolution patterns,implying informative temporal dependencies between events.Recently,many extrapolation works on TKGs have been devoted to modelling these evolutional patterns,but the task is still far from resolved because most existing works simply rely on encoding these patterns into entity representations while overlooking the significant information implied by relations of evolutional patterns.However,the authors realise that the temporal dependencies inherent in the relations of these event evolution patterns may guide the follow-up event prediction to some extent.To this end,a Temporal Relational Context-based Temporal Dependencies Learning Network(TRenD)is proposed to explore the temporal context of relations for more comprehensive learning of event evolution patterns,especially those temporal dependencies caused by interactive patterns of relations.Trend incorporates a semantic context unit to capture semantic correlations between relations,and a structural context unit to learn the interaction pattern of relations.By learning the temporal contexts of relations semantically and structurally,the authors gain insights into the underlying event evolution patterns,enabling to extract comprehensive historical information for future prediction better.Experimental results on benchmark datasets demonstrate the superiority of the model.
基金supported by the Major Key Project of PCL(Grant No.PCL2024A05)
文摘The rapid advancement of information technologies has significantly intensified the focus on cyberspace security across various sectors.In this evolving landscape,attackers deploy many techniques-including exploits,weakness identification,and complex multi-step attacks-to gain unauthorized access to systems.Conversely,defenders harness insights from a variety of sources to pinpoint potential threats.Prominent public cybersecurity databases such as the Adversarial Tactics,Techniques,and Common Knowledge(ATT&CK),Common Attack Pattern Enumeration and Classification(CAPEC),Common Vulnerabilities and Exposures(CVE),Common Weakness Enumeration(CWE),and Common Platform Enumeration(CPE)provide extensive data on security entities and their interrelations,playing a pivotal role in enriching the understanding of cybersecurity challenges and assisting in comprehensive defensive analyses.However,the semantic cross-analysis of these databases,crucial for identifying obscure threat patterns,remains underexploited.In this study,we amalgamate data from these disparate sources into a cohesive threat knowledge graph and introduce a novel knowledge representation learning approach,A4CKGE(ATT&CKCAPEC-CWE-CVE-CPE Knowledge Graph Embedding).This method utilizes advanced structural and textual analytics to predict interactions among security entities such as products,vulnerabilities,weaknesses,and multi-step attack sequences,employing complex attack templates generated through a Large Language Model(LLM).Our extensive experiments demonstrate that this approach significantly outperforms existing state-of-the-art methods in effectively predicting these relationships.The findings validate the efficacy of our threat knowledge graph in unveiling hidden connections,thereby highlighting its potential to strengthen cybersecurity defenses substantially.
基金supported by the National Natural Science Foundation of China (61702047)。
文摘Proactive dialogue generates dialogue utterance based on a conversation goal and a given knowledge graph(KG). Existing methods combine knowledge of each turn of dialogue with knowledge triples by hidden variables, resulting in the interpretability of generation results is relatively poor. An interpretable knowledge-aware path(KAP) model was proposed for knowledge reasoning in proactive dialogue generation.KAP model can transform explicit and implicit knowledge of each turn of dialogue into corresponding dialogue state matrix, thus forming the KAP for dialogue history. Based on KAP, the next turn of dialogue state vector can be infered from both the topology and semantic of KG. This vector can indicate knowledge distribution of next sentence, so it enhances the accuracy and interpretability of dialogue generation. Experiments show that KAP model’s dialogue generation is closer to actual conversation than other state-of-the-art proactive dialogue models.
基金This work was supported by the National Natural Science Foundation of China(No.U19A2059)。
文摘Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent performance.Reinforcement Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential decision problem.An intractable shortcoming of multi-hop reasoning with RL is that sparse reward signals make performance unstable.Current mainstream methods apply heuristic reward functions to counter this challenge.However,the inaccurate rewards caused by heuristic functions guide the agent to improper inference paths and unrelated object entities.To this end,we propose a novel adaptive Inverse Reinforcement Learning(IRL)framework for multi-hop reasoning,called AInvR.(1)To counter the missing and spurious paths,we replace the heuristic rule rewards with an adaptive rule reward learning mechanism based on agent’s inference trajectories;(2)to alleviate the impact of over-rewarded object entities misled by inaccurate reward shaping and rules,we propose an adaptive negative hit reward learning mechanism based on agent’s sampling strategy;(3)to further explore diverse paths and mitigate the influence of missing facts,we design a reward dropout mechanism to randomly mask and perturb reward parameters for the reward learning process.Experimental results on several benchmark knowledge graphs demonstrate that our method is more effective than existing multi-hop approaches.
基金supported in part by the National Key Research and Development Program of China(2022ZD0116405)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA27030300)the Key Research Program of the Chinese Academy of Sciences(ZDBS-SSW-JSC006)。
文摘Cross-document relation extraction(RE),as an extension of information extraction,requires integrating information from multiple documents retrieved from open domains with a large number of irrelevant or confusing noisy texts.Previous studies focus on the attention mechanism to construct the connection between different text features through semantic similarity.However,similarity-based methods cannot distinguish valid information from highly similar retrieved documents well.How to design an effective algorithm to implement aggregated reasoning in confusing information with similar features still remains an open issue.To address this problem,we design a novel local-toglobal causal reasoning(LGCR)network for cross-document RE,which enables efficient distinguishing,filtering and global reasoning on complex information from a causal perspective.Specifically,we propose a local causal estimation algorithm to estimate the causal effect,which is the first trial to use the causal reasoning independent of feature similarity to distinguish between confusing and valid information in cross-document RE.Furthermore,based on the causal effect,we propose a causality guided global reasoning algorithm to filter the confusing information and achieve global reasoning.Experimental results under the closed and the open settings of the large-scale dataset Cod RED demonstrate our LGCR network significantly outperforms the state-ofthe-art methods and validate the effectiveness of causal reasoning in confusing information processing.
基金supported by Key Laboratory of Information System Requirement,No.LHZZ202202Natural Science Foundation of Xinjiang Uyghur Autonomous Region(2023D01C55)Scientific Research Program of the Higher Education Institution of Xinjiang(XJEDU2023P127).
文摘In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.
基金supported by the National Natural Science Foundation of China under Grant 71671103
文摘It is desired to obtain the joint probability distribution(JPD) over a set of random variables with local data, so as to avoid the hard work to collect statistical data in the scale of all variables. A lot of work has been done when all variables are in a known directed acyclic graph(DAG). However, steady directed cyclic graphs(DCGs) may be involved when we simply combine modules containing local data together, where a module is composed of a child variable and its parent variables. So far, the physical and statistical meaning of steady DCGs remain unclear and unsolved. This paper illustrates the physical and statistical meaning of steady DCGs, and presents a method to calculate the JPD with local data, given that all variables are in a known single-valued Dynamic Uncertain Causality Graph(S-DUCG), and thus defines a new Bayesian Network with steady DCGs. The so-called single-valued means that only the causes of the true state of a variable are specified, while the false state is the complement of the true state.
