Universal Graph Continual Learning

TL;DR

This paper introduces a universal continual learning method for graph neural networks that effectively mitigates catastrophic forgetting across diverse graph tasks by maintaining structural knowledge through rehearsal mechanisms.

Contribution

It presents a novel universal approach for graph continual learning that handles both node and graph classification tasks, outperforming existing methods.

Findings

Significant improvement in average performance across tasks.

Reduced forgetting compared to baseline methods.

Effective handling of diverse graph learning tasks.

Abstract

We address catastrophic forgetting issues in graph learning as incoming data transits from one to another graph distribution. Whereas prior studies primarily tackle one setting of graph continual learning such as incremental node classification, we focus on a universal approach wherein each data point in a task can be a node or a graph, and the task varies from node to graph classification. We propose a novel method that enables graph neural networks to excel in this universal setting. Our approach perseveres knowledge about past tasks through a rehearsal mechanism that maintains local and global structure consistency across the graphs. We benchmark our method against various continual learning baselines in real-world graph datasets and achieve significant improvement in average performance and forgetting across tasks.