Ye Wang, Binxing Fang, Shuxian Huang, Kai Chen, Yan Jia, Aiping Li
{"title":"Extrapolation Reasoning on Temporal Knowledge Graphs via Temporal Dependencies Learning","authors":"Ye Wang, Binxing Fang, Shuxian Huang, Kai Chen, Yan Jia, Aiping Li","doi":"10.1049/cit2.70013","DOIUrl":null,"url":null,"abstract":"<p>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 <b><i>T</i></b><i>emporal</i> <b><i>Re</i></b><i>lational Co</i><b><i>n</i></b><i>text-based Temporal</i> <b><i>D</i></b><i>ependencies Learning Network</i> (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.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"10 3","pages":"815-826"},"PeriodicalIF":8.4000,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70013","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cit2.70013","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
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 TemporalRelational Context-based TemporalDependencies 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.
期刊介绍:
CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.