English

DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph

Social and Information Networks 2023-08-17 v2 Artificial Intelligence Machine Learning

Abstract

Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years. Compared with static graph, the dynamic graph is a comprehensive embodiment of both the intrinsic stable characteristics of nodes and the time-related dynamic preference. However, existing methods generally mix these two types of information into a single representation space, which may lead to poor explanation, less robustness, and a limited ability when applied to different downstream tasks. To solve the above problems, in this paper, we propose a novel disenTangled representation learning framework for discrete-time Dynamic graphs, namely DyTed. We specially design a temporal-clips contrastive learning task together with a structure contrastive learning to effectively identify the time-invariant and time-varying representations respectively. To further enhance the disentanglement of these two types of representation, we propose a disentanglement-aware discriminator under an adversarial learning framework from the perspective of information theory. Extensive experiments on Tencent and five commonly used public datasets demonstrate that DyTed, as a general framework that can be applied to existing methods, achieves state-of-the-art performance on various downstream tasks, as well as be more robust against noise.

Keywords

Cite

@article{arxiv.2210.10592,
  title  = {DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph},
  author = {Kaike Zhang and Qi Cao and Gaolin Fang and Bingbing Xu and Hongjian Zou and Huawei Shen and Xueqi Cheng},
  journal= {arXiv preprint arXiv:2210.10592},
  year   = {2023}
}
R2 v1 2026-06-28T04:00:02.731Z