CLDG: Contrastive Learning on Dynamic Graphs

TL;DR

CLDG introduces a framework for dynamic graph representation learning that leverages temporal translation invariance and a sampling layer to extract persistent signals, significantly improving efficiency and performance over existing methods.

Contribution

The paper proposes CLDG, a novel contrastive learning framework that effectively captures temporal invariance in dynamic graphs, reducing model complexity and training time.

Findings

Outperforms eight unsupervised baselines on seven datasets

Reduces model parameters and training time by over 2000 and 130 times respectively

Demonstrates competitiveness against semi-supervised methods

Abstract

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively.