arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.03004cs.AIcs.LG
收藏

面向时序知识图谱推理的多图结构学习

Learning Multi-graph Structure for Temporal Knowledge Graph Reasoning

School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);School of Information and Software Engineering, University of Electronic Science and Technology of China(电子科技大学信息与软件工程学院)

Jinchuan Zhang, Bei Hui, Chong Mu, Ling Tian

AI总结:

本文提出多图结构学习方法LMS,通过并发演化模式、跨时间戳查询相关性和时间戳语义依赖三个模块捕捉时序知识图谱特征,并结合自适应门控与时间感知解码器,在五个基准数据集上优于现有外推模型。

摘要:

时序知识图谱(Temporal Knowledge Graph, TKG)推理基于分布在时间戳上的历史快照预测未来事件,被称为外推(extrapolation),并已获得广泛关注。由于其在空间和时间相关性上的高度多样性与变化性,TKG推理是一项具有挑战性的任务,要求高效捕捉事实之间的并发结构和演化交互。尽管现有方法已在这一方向取得进展,但它们仍未能充分利用TKG内在表达语义的多种形式,包括跨多个时间戳的实体相关性以及时间信息的周期性。这一局限限制了它们全面反映历史依赖和未来趋势的能力。针对这些不足,本文提出了一种创新的推理方法,专注于学习多图结构(Learning Multi-graph Structure, LMS)。具体而言,LMS包含三个不同的模块,分别关注TKG中图结构知识的多个方面,包括沿时间戳的并发和演化模式、跨时间戳的查询特定相关性以及时间戳的语义依赖,从不同视角捕捉TKG特征。此外,LMS引入了一个自适应门控机制,用于有效融合沿时间戳和跨时间戳的实体表示。同时,它将时间戳语义集成到图注意力计算和时间感知解码器中,以对事件施加时间约束,并利用历史统计缩小预测范围。在五个基于事件的基准数据集上的大量实验结果表明,LMS优于最先进的外推模型,表明从多图视角建模对TKG推理具有优越性。

英文摘要:

Temporal Knowledge Graph (TKG) reasoning that forecasts future events based on historical snapshots distributed over timestamps is denoted as extrapolation and has gained significant attention. Owing to its extreme versatility and variation in spatial and temporal correlations, TKG reasoning presents a challenging task, demanding efficient capture of concurrent structures and evolutional interactions among facts. While existing methods have made strides in this direction, they still fall short of harnessing the diverse forms of intrinsic expressive semantics of TKGs, which encompass entity correlations across multiple timestamps and periodicity of temporal information. This limitation constrains their ability to thoroughly reflect historical dependencies and future trends. In response to these drawbacks, this paper proposes an innovative reasoning approach that focuses on Learning Multi-graph Structure (LMS). Concretely, it comprises three distinct modules concentrating on multiple aspects of graph structure knowledge within TKGs, including concurrent and evolutional patterns along timestamps, query-specific correlations across timestamps, and semantic dependencies of timestamps, which capture TKG features from various perspectives. Besides, LMS incorporates an adaptive gate for merging entity representations both along and across timestamps effectively. Moreover, it integrates timestamp semantics into graph attention calculations and time-aware decoders, in order to impose temporal constraints on events and narrow down prediction scopes with historical statistics. Extensive experimental results on five event-based benchmark datasets demonstrate that LMS outperforms state-of-the-art extrapolation models, indicating the superiority of modeling a multi-graph perspective for TKG reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑