Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurr...Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.展开更多
The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most exi...The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most existing frameworks typically utilize separate modules for spatial and temporal correlations modeling.However,this stepwise pattern may limit the effectiveness and efficiency in spatial-temporal feature extraction and cause the overlook of important information in some steps.Furthermore,it is lacking sufficient guidance from prior information while modeling based on a given spatial adjacency graph(e.g.,deriving from the geodesic distance or approximate connectivity),and may not reflect the actual interaction between nodes.To overcome those limitations,our paper proposes a spatial-temporal graph synchronous aggregation(STGSA)model to extract the localized and long-term spatial-temporal dependencies simultaneously.Specifically,a tailored graph aggregation method in the vertex domain is designed to extract spatial and temporal features in one graph convolution process.In each STGSA block,we devise a directed temporal correlation graph to represent the localized and long-term dependencies between nodes,and the potential temporal dependence is further fine-tuned by an adaptive weighting operation.Meanwhile,we construct an elaborated spatial adjacency matrix to represent the road sensor graph by considering both physical distance and node similarity in a datadriven manner.Then,inspired by the multi-head attention mechanism which can jointly emphasize information from different r epresentation subspaces,we construct a multi-stream module based on the STGSA blocks to capture global information.It projects the embedding input repeatedly with multiple different channels.Finally,the predicted values are generated by stacking several multi-stream modules.Extensive experiments are constructed on six real-world datasets,and numerical results show that the proposed STGSA model significantly outperforms the benchmarks.展开更多
Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the ...Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the data during critical events.A skeleton representation of the human body has been proven to be effective for this task.The skeletons are presented in graphs form-like.However,the topology of a graph is not structured like Euclideanbased data.Therefore,a new set of methods to perform the convolution operation upon the skeleton graph is proposed.Our proposal is based on the Spatial Temporal-Graph Convolutional Network(ST-GCN)framework.In this study,we proposed an improved set of label mapping methods for the ST-GCN framework.We introduce three split techniques(full distance split,connection split,and index split)as an alternative approach for the convolution operation.The experiments presented in this study have been trained using two benchmark datasets:NTU-RGB+D and Kinetics to evaluate the performance.Our results indicate that our split techniques outperform the previous partition strategies and aremore stable during training without using the edge importance weighting additional training parameter.Therefore,our proposal can provide a more realistic solution for real-time applications centred on daily living recognition systems activities for indoor environments.展开更多
Edge closeness and betweenness centralities are widely used path-based metrics for characterizing the importance of edges in networks.In general graphs,edge closeness centrality indicates the importance of edges by th...Edge closeness and betweenness centralities are widely used path-based metrics for characterizing the importance of edges in networks.In general graphs,edge closeness centrality indicates the importance of edges by the shortest distances from the edge to all the other vertices.Edge betweenness centrality ranks which edges are significant based on the fraction of all-pairs shortest paths that pass through the edge.Nowadays,extensive research efforts go into centrality computation over general graphs that omit time dimension.However,numerous real-world networks are modeled as temporal graphs,where the nodes are related to each other at different time instances.The temporal property is important and should not be neglected because it guides the flow of information in the network.This state of affairs motivates the paper’s study of edge centrality computation methods on temporal graphs.We introduce the concepts of the label,and label dominance relation,and then propose multi-thread parallel labeling-based methods on OpenMP to efficiently compute edge closeness and betweenness centralities w.r.t.three types of optimal temporal paths.For edge closeness centrality computation,a time segmentation strategy and two observations are presented to aggregate some related temporal edges for uniform processing.For edge betweenness centrality computation,to improve efficiency,temporal edge dependency formulas,a labeling-based forward-backward scanning strategy,and a compression-based optimization method are further proposed to iteratively accumulate centrality values.Extensive experiments using 13 real temporal graphs are conducted to provide detailed insights into the efficiency and effectiveness of the proposed methods.Compared with state-ofthe-art methods,labeling-based methods are capable of up to two orders of magnitude speedup.展开更多
The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision field.Therefore,finding efficient solutions to extrac...The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision field.Therefore,finding efficient solutions to extract knowledge from these sources is imperative.Recently,the BlazePose system has been released for skeleton extraction from images oriented to mobile devices.With this skeleton graph representation in place,a Spatial-Temporal Graph Convolutional Network can be implemented to predict the action.We hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest,it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR tasks.Hence,in this study,we present the first implementation of the BlazePose skeleton topology upon this architecture for action recognition.Moreover,we propose the Enhanced-BlazePose topology that can achieve better results than its predecessor.Additionally,we propose different skeleton detection thresholds that can improve the accuracy performance even further.We reached a top-1 accuracy performance of 40.1%on the Kinetics dataset.For the NTU-RGB+D dataset,we achieved 87.59%and 92.1%accuracy for Cross-Subject and Cross-View evaluation criteria,respectively.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
Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling com...Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling complex systems.Different types of events continually occur,which are often related to historical and concurrent events.In this paper,we formalize the future event prediction as a temporal knowledge graph reasoning problem.Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process.As a result,they cannot effectively reason over temporal knowledge graphs and predict events happening in the future.To address this problem,some recent works learn to infer future events based on historical eventbased temporal knowledge graphs.However,these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously.This paper proposes a new graph representation learning model,namely Recurrent Event Graph ATtention Network(RE-GAT),based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently.More specifically,our RE-GAT uses an attention-based historical events embedding module to encode past events,and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp.A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations.We evaluate our proposed method on four benchmark datasets.Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various base-lines,which proves that our method can more accurately predict what events are going to happen.展开更多
Predicting potential facts in the future,Temporal Knowledge Graph(TKG)extrapolation remains challenging because of the deep dependence between the temporal association and semantic patterns of facts.Intuitively,facts(...Predicting potential facts in the future,Temporal Knowledge Graph(TKG)extrapolation remains challenging because of the deep dependence between the temporal association and semantic patterns of facts.Intuitively,facts(events)that happened at different timestamps have different influences on future events,which can be attributed to a hierarchy among not only facts but also relevant entities.Therefore,it is crucial to pay more attention to important entities and events when forecasting the future.However,most existing methods focus on reasoning over temporally evolving facts or mining evolutional patterns from known facts,which may be affected by the diversity and variability of the evolution,and they might fail to attach importance to facts that matter.Hyperbolic geometry was proved to be effective in capturing hierarchical patterns among data,which is considered to be a solution for modelling hierarchical relations among facts.To this end,we propose ReTIN,a novel model integrating real-time influence of historical facts for TKG reasoning based on hyperbolic geometry,which provides low-dimensional embeddings to capture latent hierarchical structures and other rich semantic patterns of the existing TKG.Considering both real-time and global features of TKG boosts the adaptation of ReTIN to the ever-changing dynamics and inherent constraints.Extensive experiments on benchmarks demonstrate the superiority of ReTIN over various baselines.The ablation study further supports the value of exploiting temporal information.展开更多
As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks ...As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks and deep question and answer(Q&A).Current research mainly fo-cuses on the completion of static knowledge graphs,and the temporal information in temporal knowl-edge graphs(TKGs)is ignored.However,the temporal information is definitely very helpful for the completion.Note that existing researches on temporal knowledge graph completion are difficult to process temporal information and to integrate entities,relations and time well.In this work,a rotation and scaling(RotatS)model is proposed,which learns rotation and scaling transformations from head entity embedding to tail entity embedding in 3D spaces to capture the information of time and rela-tions in the temporal knowledge graph.The performance of the proposed RotatS model have been evaluated by comparison with several baselines under similar experimental conditions and space com-plexity on four typical knowl good graph completion datasets publicly available online.The study shows that RotatS can achieve good results in terms of prediction accuracy.展开更多
The ability to forecast future events brings great benefits for society and cyberspace in many public safety domains,such as civil unrest,pandemics and crimes.The occurrences of new events are often correlated or depe...The ability to forecast future events brings great benefits for society and cyberspace in many public safety domains,such as civil unrest,pandemics and crimes.The occurrences of new events are often correlated or dependent on historical and concurrent events.Many existing studies learn event-occurring processes with sequential and structural models,which,however,suffer from inefficient and inaccurate prediction problems.To better understand the event forecasting task and characterize the occurrence of new events,we exploit the human cognitive theory from the cognitive neuroscience discipline to find available cues for algorithm design and event prediction.Motivated by the dual process theory,we propose a two-stage learning scheme for event knowledge mining and prediction.First,we screen out event candidates based on historical inherent knowledge.Then we re-rank event candidates by probing into the newest relative events.Our proposed model mimics a sociological phenomenon called“the chameleon effect”and consists of a new target attentive graph collaborative learning mechanism to ensure a better understanding of sophisticated evolution patterns associated with events.In addition,self-supervised contrastive learning is employed to alleviate the over-smoothing problem that existed in graph learning while improving the model’s interpretability.Experiments show the effectiveness of our approach.展开更多
The global clustering of inventive talent shapes innovation capacity and drives economic growth.For China,this process is especially crucial in sustaining its development momentum.This paper draws on data from the EPO...The global clustering of inventive talent shapes innovation capacity and drives economic growth.For China,this process is especially crucial in sustaining its development momentum.This paper draws on data from the EPO Worldwide Patent Statistical Database(PATSTAT)to extract global inventive talent mobility information and analyzes the spatial structural evolution of the global inventive talent flow network.The study finds that this network is undergoing a multi-polar transformation,characterized by the rising importance of a few central countries-such as the United States,Germany,and China-and the increasing marginalization of many peripheral countries.In response to this typical phenomenon,the paper constructs an endogenous migration model and conducts empirical testing using the Temporal Exponential Random Graph Model(TERGM).The results reveal several endogenous mechanisms driving global inventive talent flows,including reciprocity,path dependence,convergence effects,transitivity,and cyclic structures,all of which contribute to the network’s multi-polar trend.In addition,differences in regional industrial structures significantly influence talent mobility choices and are a decisive factor in the formation of poles within the multi-polar landscape.Based on these findings,it is suggested that efforts be made to foster two-way channels for talent exchange between China and other global innovation hubs,in order to enhance international collaboration and knowledge flow.We should aim to reduce the migration costs and institutional barriers faced by R&D personnel,thereby encouraging greater mobility of high-skilled talent.Furthermore,the government is advised to strategically leverage regional strengths in high-tech industries as a lever to capture competitive advantages in emerging technologies and products,ultimately strengthening the country’s position in the global innovation landscape.展开更多
In this article, the notion of pinning control for directed networks of dynamical systems is introduced, where the nodes could be either single-input single-output （SISO） or multi-input multi-output （MIMO） dynamic...In this article, the notion of pinning control for directed networks of dynamical systems is introduced, where the nodes could be either single-input single-output （SISO） or multi-input multi-output （MIMO） dynamical systems, and could be non-identical and nonlinear in general but will be specified to be identical linear time-invariant （LTI） systems here in the study of network controllability. Both state and structural controllability problems will be discussed, illustrating how the network topology, node-system dynamics, external control inputs and inner dynamical interactions altogether affect the controllability of a general complex network of LTI systems, with necessary and sufficient conditions presented for both SISO and MIMO settings. To that end, the controllability of a special temporally switching directed network of linear time-varying （LTV） node systems will be addressed, leaving some more general networks and challenging issues to the end for research outlook.展开更多
Top-k ranking of websites according to traffic volume is important for Internet Service Providers(ISPs) to understand network status and optimize network resources. However, the ranking result always has a big deviati...Top-k ranking of websites according to traffic volume is important for Internet Service Providers(ISPs) to understand network status and optimize network resources. However, the ranking result always has a big deviation with actual rank for the existence of unknown web traffic, which cannot be identified accurately under current techniques. In this paper, we introduce a novel method to approximate the actual rank. This method associates unknown web traffic with websites according to statistical probabilities. Then, we construct a probabilistic top-k query model to rank websites. We conduct several experiments by using real HTTP traffic traces collected from a commercial ISP covering an entire city in northern China. Experimental results show that the proposed techniques can reduce the deviation existing between the ground truth and the ranking results vastly. In addition, we find that the websites providing video service have higher ratio of unknown IP as well as higher ratio of unknown traffic than the websites providing text web page service. Specifically, we find that the top-3 video websites have more than 90% of unknown web traffic. All these findings are helpful for ISPs understanding network status and deploying Content Distributed Network(CDN).展开更多
Despite the growing interest in exploring the interdisciplinary collaboration patterns and the factors in relation to team assembly in the first place, the dynamics of interdisciplinary collaboration with time varying...Despite the growing interest in exploring the interdisciplinary collaboration patterns and the factors in relation to team assembly in the first place, the dynamics of interdisciplinary collaboration with time varying is hardly known. Based on the longitudinally co-authorship network perspective, the paper investigates the evolutionary dynamics of interdisciplinary collaboration using separable temporal exponential-family random graph model(STERGM). The results from STERGM show that structural properties, properties of researcher and link properties affect the evolution of interdisciplinary co-authorship network to varying degrees. Network transitivity and preferential attachment play a decisive role in formation of links and hamper dissolution of ties in the network. The number of collaborators of interdisciplinary researchers plays an active role in the formation of partnerships and hamper dissolution of partnerships in the initial stage;specialization of team members inhibits the establishment of collaborative relationship in the initial stage and promotes the dissolution of connections in the later stage of project;the large difference in specialization value between members is not conducive to the formation of relations in the initial stage, but conducive to the maintenance of collaborative relations after links establishment. The same discipline background is conducive to the formation of relations but not conducive to the maintenance of collaborative relationships in interdisciplinary co-author network.展开更多
基金the National Natural Science Founda-tion of China(62062062)hosted by Gulila Altenbek.
文摘Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.
基金partially supported by the National Key Research and Development Program of China(2020YFB2104001)。
文摘The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most existing frameworks typically utilize separate modules for spatial and temporal correlations modeling.However,this stepwise pattern may limit the effectiveness and efficiency in spatial-temporal feature extraction and cause the overlook of important information in some steps.Furthermore,it is lacking sufficient guidance from prior information while modeling based on a given spatial adjacency graph(e.g.,deriving from the geodesic distance or approximate connectivity),and may not reflect the actual interaction between nodes.To overcome those limitations,our paper proposes a spatial-temporal graph synchronous aggregation(STGSA)model to extract the localized and long-term spatial-temporal dependencies simultaneously.Specifically,a tailored graph aggregation method in the vertex domain is designed to extract spatial and temporal features in one graph convolution process.In each STGSA block,we devise a directed temporal correlation graph to represent the localized and long-term dependencies between nodes,and the potential temporal dependence is further fine-tuned by an adaptive weighting operation.Meanwhile,we construct an elaborated spatial adjacency matrix to represent the road sensor graph by considering both physical distance and node similarity in a datadriven manner.Then,inspired by the multi-head attention mechanism which can jointly emphasize information from different r epresentation subspaces,we construct a multi-stream module based on the STGSA blocks to capture global information.It projects the embedding input repeatedly with multiple different channels.Finally,the predicted values are generated by stacking several multi-stream modules.Extensive experiments are constructed on six real-world datasets,and numerical results show that the proposed STGSA model significantly outperforms the benchmarks.
文摘Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the data during critical events.A skeleton representation of the human body has been proven to be effective for this task.The skeletons are presented in graphs form-like.However,the topology of a graph is not structured like Euclideanbased data.Therefore,a new set of methods to perform the convolution operation upon the skeleton graph is proposed.Our proposal is based on the Spatial Temporal-Graph Convolutional Network(ST-GCN)framework.In this study,we proposed an improved set of label mapping methods for the ST-GCN framework.We introduce three split techniques(full distance split,connection split,and index split)as an alternative approach for the convolution operation.The experiments presented in this study have been trained using two benchmark datasets:NTU-RGB+D and Kinetics to evaluate the performance.Our results indicate that our split techniques outperform the previous partition strategies and aremore stable during training without using the edge importance weighting additional training parameter.Therefore,our proposal can provide a more realistic solution for real-time applications centred on daily living recognition systems activities for indoor environments.
基金supported by the National Natural Science Foundation of China(Grant Nos.62302451 and 62276233)the Natural Science Foundation of Zhejiang Province of China(No.LQ22F020018)the Key Research Project of Zhejiang Province of China(No.2023C01048).
文摘Edge closeness and betweenness centralities are widely used path-based metrics for characterizing the importance of edges in networks.In general graphs,edge closeness centrality indicates the importance of edges by the shortest distances from the edge to all the other vertices.Edge betweenness centrality ranks which edges are significant based on the fraction of all-pairs shortest paths that pass through the edge.Nowadays,extensive research efforts go into centrality computation over general graphs that omit time dimension.However,numerous real-world networks are modeled as temporal graphs,where the nodes are related to each other at different time instances.The temporal property is important and should not be neglected because it guides the flow of information in the network.This state of affairs motivates the paper’s study of edge centrality computation methods on temporal graphs.We introduce the concepts of the label,and label dominance relation,and then propose multi-thread parallel labeling-based methods on OpenMP to efficiently compute edge closeness and betweenness centralities w.r.t.three types of optimal temporal paths.For edge closeness centrality computation,a time segmentation strategy and two observations are presented to aggregate some related temporal edges for uniform processing.For edge betweenness centrality computation,to improve efficiency,temporal edge dependency formulas,a labeling-based forward-backward scanning strategy,and a compression-based optimization method are further proposed to iteratively accumulate centrality values.Extensive experiments using 13 real temporal graphs are conducted to provide detailed insights into the efficiency and effectiveness of the proposed methods.Compared with state-ofthe-art methods,labeling-based methods are capable of up to two orders of magnitude speedup.
文摘The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision field.Therefore,finding efficient solutions to extract knowledge from these sources is imperative.Recently,the BlazePose system has been released for skeleton extraction from images oriented to mobile devices.With this skeleton graph representation in place,a Spatial-Temporal Graph Convolutional Network can be implemented to predict the action.We hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest,it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR tasks.Hence,in this study,we present the first implementation of the BlazePose skeleton topology upon this architecture for action recognition.Moreover,we propose the Enhanced-BlazePose topology that can achieve better results than its predecessor.Additionally,we propose different skeleton detection thresholds that can improve the accuracy performance even further.We reached a top-1 accuracy performance of 40.1%on the Kinetics dataset.For the NTU-RGB+D dataset,we achieved 87.59%and 92.1%accuracy for Cross-Subject and Cross-View evaluation criteria,respectively.
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 National Natural Science Foundation of China under grants U19B2044National Key Research and Development Program of China(2021YFC3300500).
文摘Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling complex systems.Different types of events continually occur,which are often related to historical and concurrent events.In this paper,we formalize the future event prediction as a temporal knowledge graph reasoning problem.Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process.As a result,they cannot effectively reason over temporal knowledge graphs and predict events happening in the future.To address this problem,some recent works learn to infer future events based on historical eventbased temporal knowledge graphs.However,these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously.This paper proposes a new graph representation learning model,namely Recurrent Event Graph ATtention Network(RE-GAT),based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently.More specifically,our RE-GAT uses an attention-based historical events embedding module to encode past events,and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp.A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations.We evaluate our proposed method on four benchmark datasets.Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various base-lines,which proves that our method can more accurately predict what events are going to happen.
基金Major Key Project of Pengcheng Laboratory,Grant/Award Number:PCL2022A03。
文摘Predicting potential facts in the future,Temporal Knowledge Graph(TKG)extrapolation remains challenging because of the deep dependence between the temporal association and semantic patterns of facts.Intuitively,facts(events)that happened at different timestamps have different influences on future events,which can be attributed to a hierarchy among not only facts but also relevant entities.Therefore,it is crucial to pay more attention to important entities and events when forecasting the future.However,most existing methods focus on reasoning over temporally evolving facts or mining evolutional patterns from known facts,which may be affected by the diversity and variability of the evolution,and they might fail to attach importance to facts that matter.Hyperbolic geometry was proved to be effective in capturing hierarchical patterns among data,which is considered to be a solution for modelling hierarchical relations among facts.To this end,we propose ReTIN,a novel model integrating real-time influence of historical facts for TKG reasoning based on hyperbolic geometry,which provides low-dimensional embeddings to capture latent hierarchical structures and other rich semantic patterns of the existing TKG.Considering both real-time and global features of TKG boosts the adaptation of ReTIN to the ever-changing dynamics and inherent constraints.Extensive experiments on benchmarks demonstrate the superiority of ReTIN over various baselines.The ablation study further supports the value of exploiting temporal information.
基金the National Natural Science Foundation of China(No.6187022153).
文摘As the research of knowledge graph(KG)is deepened and widely used,knowledge graph com-pletion(KGC)has attracted more and more attentions from researchers,especially in scenarios of in-telligent search,social networks and deep question and answer(Q&A).Current research mainly fo-cuses on the completion of static knowledge graphs,and the temporal information in temporal knowl-edge graphs(TKGs)is ignored.However,the temporal information is definitely very helpful for the completion.Note that existing researches on temporal knowledge graph completion are difficult to process temporal information and to integrate entities,relations and time well.In this work,a rotation and scaling(RotatS)model is proposed,which learns rotation and scaling transformations from head entity embedding to tail entity embedding in 3D spaces to capture the information of time and rela-tions in the temporal knowledge graph.The performance of the proposed RotatS model have been evaluated by comparison with several baselines under similar experimental conditions and space com-plexity on four typical knowl good graph completion datasets publicly available online.The study shows that RotatS can achieve good results in terms of prediction accuracy.
基金supported by the National Natural Science Foundation of China(Nos.62176043 and 62072077)the Grant SCITLAB-30002 of Intelligent Terminal Key Laboratory of Sichuan Province.
文摘The ability to forecast future events brings great benefits for society and cyberspace in many public safety domains,such as civil unrest,pandemics and crimes.The occurrences of new events are often correlated or dependent on historical and concurrent events.Many existing studies learn event-occurring processes with sequential and structural models,which,however,suffer from inefficient and inaccurate prediction problems.To better understand the event forecasting task and characterize the occurrence of new events,we exploit the human cognitive theory from the cognitive neuroscience discipline to find available cues for algorithm design and event prediction.Motivated by the dual process theory,we propose a two-stage learning scheme for event knowledge mining and prediction.First,we screen out event candidates based on historical inherent knowledge.Then we re-rank event candidates by probing into the newest relative events.Our proposed model mimics a sociological phenomenon called“the chameleon effect”and consists of a new target attentive graph collaborative learning mechanism to ensure a better understanding of sophisticated evolution patterns associated with events.In addition,self-supervised contrastive learning is employed to alleviate the over-smoothing problem that existed in graph learning while improving the model’s interpretability.Experiments show the effectiveness of our approach.
基金supported by the Major Project of the National Social Science Fund of China,titled“Design Path Selection for the Mechanism of New and Old Growth Driver Conversion”(Grant No.18ZDA077)by the Joint Special Major Research Project of the Yangtze River Delta Economics and Social Development Research Center at Nanjing University and the Collaborative Innovation Center for China Economy(CICCE),titled“Practicing Innovation in China’s Development Economics for the Yangtze River Delta:From Industrial Clusters to Technological Clusters”(Grant No.CYD2022006).
文摘The global clustering of inventive talent shapes innovation capacity and drives economic growth.For China,this process is especially crucial in sustaining its development momentum.This paper draws on data from the EPO Worldwide Patent Statistical Database(PATSTAT)to extract global inventive talent mobility information and analyzes the spatial structural evolution of the global inventive talent flow network.The study finds that this network is undergoing a multi-polar transformation,characterized by the rising importance of a few central countries-such as the United States,Germany,and China-and the increasing marginalization of many peripheral countries.In response to this typical phenomenon,the paper constructs an endogenous migration model and conducts empirical testing using the Temporal Exponential Random Graph Model(TERGM).The results reveal several endogenous mechanisms driving global inventive talent flows,including reciprocity,path dependence,convergence effects,transitivity,and cyclic structures,all of which contribute to the network’s multi-polar trend.In addition,differences in regional industrial structures significantly influence talent mobility choices and are a decisive factor in the formation of poles within the multi-polar landscape.Based on these findings,it is suggested that efforts be made to foster two-way channels for talent exchange between China and other global innovation hubs,in order to enhance international collaboration and knowledge flow.We should aim to reduce the migration costs and institutional barriers faced by R&D personnel,thereby encouraging greater mobility of high-skilled talent.Furthermore,the government is advised to strategically leverage regional strengths in high-tech industries as a lever to capture competitive advantages in emerging technologies and products,ultimately strengthening the country’s position in the global innovation landscape.
文摘In this article, the notion of pinning control for directed networks of dynamical systems is introduced, where the nodes could be either single-input single-output （SISO） or multi-input multi-output （MIMO） dynamical systems, and could be non-identical and nonlinear in general but will be specified to be identical linear time-invariant （LTI） systems here in the study of network controllability. Both state and structural controllability problems will be discussed, illustrating how the network topology, node-system dynamics, external control inputs and inner dynamical interactions altogether affect the controllability of a general complex network of LTI systems, with necessary and sufficient conditions presented for both SISO and MIMO settings. To that end, the controllability of a special temporally switching directed network of linear time-varying （LTV） node systems will be addressed, leaving some more general networks and challenging issues to the end for research outlook.
基金supported by 111 Project of China under Grant No.B08004
文摘Top-k ranking of websites according to traffic volume is important for Internet Service Providers(ISPs) to understand network status and optimize network resources. However, the ranking result always has a big deviation with actual rank for the existence of unknown web traffic, which cannot be identified accurately under current techniques. In this paper, we introduce a novel method to approximate the actual rank. This method associates unknown web traffic with websites according to statistical probabilities. Then, we construct a probabilistic top-k query model to rank websites. We conduct several experiments by using real HTTP traffic traces collected from a commercial ISP covering an entire city in northern China. Experimental results show that the proposed techniques can reduce the deviation existing between the ground truth and the ranking results vastly. In addition, we find that the websites providing video service have higher ratio of unknown IP as well as higher ratio of unknown traffic than the websites providing text web page service. Specifically, we find that the top-3 video websites have more than 90% of unknown web traffic. All these findings are helpful for ISPs understanding network status and deploying Content Distributed Network(CDN).
文摘Despite the growing interest in exploring the interdisciplinary collaboration patterns and the factors in relation to team assembly in the first place, the dynamics of interdisciplinary collaboration with time varying is hardly known. Based on the longitudinally co-authorship network perspective, the paper investigates the evolutionary dynamics of interdisciplinary collaboration using separable temporal exponential-family random graph model(STERGM). The results from STERGM show that structural properties, properties of researcher and link properties affect the evolution of interdisciplinary co-authorship network to varying degrees. Network transitivity and preferential attachment play a decisive role in formation of links and hamper dissolution of ties in the network. The number of collaborators of interdisciplinary researchers plays an active role in the formation of partnerships and hamper dissolution of partnerships in the initial stage;specialization of team members inhibits the establishment of collaborative relationship in the initial stage and promotes the dissolution of connections in the later stage of project;the large difference in specialization value between members is not conducive to the formation of relations in the initial stage, but conducive to the maintenance of collaborative relations after links establishment. The same discipline background is conducive to the formation of relations but not conducive to the maintenance of collaborative relationships in interdisciplinary co-author network.
