Universal Graph Continual Learning
This addresses a critical problem for researchers and practitioners in graph machine learning by offering a more flexible solution, though it appears incremental as it builds on existing rehearsal mechanisms.
The paper tackles catastrophic forgetting in graph learning across varying graph distributions and task types, proposing a universal approach that improves average performance and reduces forgetting across tasks.
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.