arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.01974cs.SIcs.AIcs.LG
收藏

用于无标度社区结构时序知识图谱推理的基于 Hawkes 的表示学习

Hawkes based Representation Learning for Reasoning over Scale-free Community-structured Temporal Knowledge Graphs

School of Software, Dalian University of Technology(大连理工大学软件学院)

Yuwei Du, Xinyue Liu, Wenxin Liang, Linlin Zong, Xianchao Zhang

AI总结:

针对真实 TKG 的社区结构、无标度长尾分布与事件时间衰减特征,提出 HERLN,通过社区发现、Hawkes 关系图卷积网络和条件解码提升推理性能。

摘要:

时序知识图谱(TKG)推理因其在许多实际任务中的巨大价值而成为热门研究课题。TKG 推理的关键在于对 TKG 的结构信息和演化模式进行建模。尽管已有大量工作致力于 TKG 推理,但真实世界网络的结构与演化特征尚未得到考虑。在结构方面,真实世界网络通常表现出明显的社区结构和无标度(长尾分布)特性。在演化方面,事件的影响会随时间流逝而衰减。本文提出一种名为基于 Hawkes 过程的演化表示学习网络(HERLN)的新型 TKG 推理模型,该模型同时学习 TKG 的结构信息和演化模式,并考虑真实世界网络的特征:社区结构、无标度性和时间衰减。首先,我们在输入 TKG 中发现社区,使编码获得更相似的社区内嵌入。其次,我们设计了一种基于 Hawkes 过程的关系图卷积网络,以应对事件影响衰减现象。第三,我们设计了一种条件解码方法,以缓解长尾分布导致的对频繁实体的偏差。实验结果表明,HERLN 相比最先进模型取得了显著提升。

英文摘要:

Temporal knowledge graph (TKG) reasoning has become a hot topic due to its great value in many practical tasks. The key to TKG reasoning is modeling the structural information and evolutional patterns of the TKGs. While great efforts have been devoted to TKG reasoning, the structural and evolutional characteristics of real-world networks have not been considered. In the aspect of structure, real-world networks usually exhibit clear community structure and scale-free (long-tailed distribution) properties. In the aspect of evolution, the impact of an event decays with the time elapsing. In this paper, we propose a novel TKG reasoning model called Hawkes process-based Evolutional Representation Learning Network (HERLN), which learns structural information and evolutional patterns of a TKG simultaneously, considering the characteristics of real-world networks: community structure, scale-free and temporal decaying. First, we find communities in the input TKG to make the encoding get more similar intra-community embeddings. Second, we design a Hawkes process-based relational graph convolutional network to cope with the event impact-decaying phenomenon. Third, we design a conditional decoding method to alleviate biases towards frequent entities caused by long-tailed distribution. Experimental results show that HERLN achieves significant improvements over the state-of-the-art models.

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。

↑