arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.02457cs.AI
收藏

时序知识图谱补全综述:分类体系、研究进展与未来展望

A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects

Beijing University of Technology(北京工业大学);Beijing Artificial Intelligence Institute(北京人工智能研究院);Dakota State University(达科他州立大学);Griffith University(格里菲斯大学);University of Stuttgart(斯图加特大学);Monash University(莫纳什大学);Peking University(北京大学)

Jiapu Wang, Boyue Wang, Meikang Qiu, Shirui Pan, Bo Xiong, Heng Liu, Linhao Luo, Tengfei Liu, Yongli Hu, Baocai Yin, Wen Gao

AI总结:

本文系统综述了时序知识图谱补全方法,从背景、插值与外推三个层面梳理现有技术、数据集和评估协议,并指出挑战与未来方向。

摘要:

时间特性在大量知识中表现显著,这凸显了时序知识图谱(TKGs)在学术界和工业界的关键作用。然而,TKGs 常常因三个主要原因而不完整:新知识的持续涌现、从非结构化数据中提取结构化信息的算法能力不足,以及源数据集中信息的缺乏。因此,时序知识图谱补全(TKGC)任务引起了越来越多的关注,其目标是根据可用信息预测缺失项。本文对 TKGC 方法及其细节进行了全面综述。具体而言,本文主要由三个部分组成,即:1)背景,涵盖 TKGC 方法的预备知识、训练所需的损失函数,以及数据集和评估协议;2)插值,通过相关的可用信息估计和预测缺失元素或元素集合,并根据处理时间信息的方式进一步对相关 TKGC 方法进行分类;3)外推,通常关注连续 TKGs 并预测未来事件,然后根据所采用的算法对所有外推方法进行分类。我们进一步指出了 TKGC 面临的挑战并讨论了未来的研究方向。

英文摘要:

Temporal characteristics are prominently evident in a substantial volume of knowledge, which underscores the pivotal role of Temporal Knowledge Graphs (TKGs) in both academia and industry. However, TKGs often suffer from incompleteness for three main reasons: the continuous emergence of new knowledge, the weakness of the algorithm for extracting structured information from unstructured data, and the lack of information in the source dataset. Thus, the task of Temporal Knowledge Graph Completion (TKGC) has attracted increasing attention, aiming to predict missing items based on the available information. In this paper, we provide a comprehensive review of TKGC methods and their details. Specifically, this paper mainly consists of three components, namely, 1)Background, which covers the preliminaries of TKGC methods, loss functions required for training, as well as the dataset and evaluation protocol; 2)Interpolation, that estimates and predicts the missing elements or set of elements through the relevant available information. It further categorizes related TKGC methods based on how to process temporal information; 3)Extrapolation, which typically focuses on continuous TKGs and predicts future events, and then classifies all extrapolation methods based on the algorithms they utilize. We further pinpoint the challenges and discuss future research directions of TKGC.

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。

↑