arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.07782cs.AI
收藏

时态知识图谱推理的复杂进化模式学习

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司)

Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng

摘要:

时间知识图谱(TKG)是对应于不同时间戳的KG的序列。TKG推理旨在根据历史KG序列预测未来的潜在事实。这项任务的关键之一是从这些序列中挖掘和理解事实的进化模式。其演化模式具有长度多样性和时变性两个方面的复杂性。现有的TKG推理模型主要关注于对固定长度的事实序列进行建模,无法发现长度变化的复杂进化模式。针对这些模型都是离线训练的,不能很好地适应进化模式的变化,本文提出了一种新的模型--复杂进化网络(Complex Evolutionary Network,CEN),该模型使用一种长度感知的卷积神经网络(CNN),通过由易到难的课程学习策略来处理不同长度的进化模式。此外,我们建议在在线环境下学习模型,使其能够适应随时间变化的进化模式。大量的实验表明,CEN在传统的离线和在线设置下都获得了显着的性能改善。

英文摘要:

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine and understand evolutional patterns of facts from these sequences. The evolutional patterns are complex in two aspects, length-diversity and time-variability. Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on. Thus, we propose a new model, called Complex Evolutional Network (CEN), which uses a length-aware Convolutional Neural Network (CNN) to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. Besides, we propose to learn the model under the online setting so that it can adapt to the changes of evolutional patterns over time. Extensive experiments demonstrate that CEN obtains substantial performance improvement under both the traditional offline and the proposed online settings.

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。

↑