Pre-Training on Dynamic Graph Neural Networks

TL;DR

This paper introduces PT-DGNN, a pre-training approach for dynamic graph neural networks that captures structural, semantic, and evolutionary features, improving link prediction on real-world datasets.

Contribution

It presents a novel pre-training method specifically designed for dynamic graphs, incorporating dynamic sub-graph sampling and generation tasks to learn evolution features.

Findings

Achieves state-of-the-art results on link prediction tasks

Effectively captures dynamic network evolution features

Outperforms existing static pre-training methods

Abstract

The pre-training on the graph neural network model can learn the general features of large-scale networks or networks of the same type by self-supervised methods, which allows the model to work even when node labels are missing. However, the existing pre-training methods do not take network evolution into consideration. This paper proposes a pre-training method on dynamic graph neural networks (PT-DGNN), which uses dynamic attributed graph generation tasks to simultaneously learn the structure, semantics, and evolution features of the graph. The method includes two steps: 1) dynamic sub-graph sampling, and 2) pre-training with dynamic attributed graph generation task. Comparative experiments on three realistic dynamic network datasets show that the proposed method achieves the best results on the link prediction fine-tuning task.