TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning

TL;DR

This paper introduces TCL, a novel transformer-based dynamic graph neural network that leverages contrastive learning to effectively capture temporal and topological information, improving interaction prediction in evolving graphs.

Contribution

We propose a new graph transformer model with a two-stream encoder and contrastive learning, enabling scalable and effective dynamic node representations for evolving graphs.

Findings

Outperforms existing methods on four benchmark datasets

Effectively captures both temporal and topological information

First application of contrastive learning to dynamic graph representation

Abstract

Dynamic graph modeling has recently attracted much attention due to its extensive applications in many real-world scenarios, such as recommendation systems, financial transactions, and social networks. Although many works have been proposed for dynamic graph modeling in recent years, effective and scalable models are yet to be developed. In this paper, we propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion and enables effective dynamic node representation learning that captures both the temporal and topology information. Technically, our model contains three novel aspects. First, we generalize the vanilla Transformer to temporal graph learning scenarios and design a graph-topology-aware transformer. Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level. Lastly, we are inspired by the recently developed contrastive learning and propose to optimize our model by maximizing mutual information (MI) between the predictive representations of two future interaction nodes. Benefiting from this, our dynamic representations can preserve high-level (or global) semantics about interactions and thus is robust to noisy interactions. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs. We evaluate our model on four benchmark datasets for interaction prediction and experiment results demonstrate the superiority of our model.