Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification

TL;DR

This paper investigates catastrophic forgetting in deep graph networks, evaluating classical continual learning methods and regularization techniques on graph classification tasks, and provides a benchmark and software tools for future research.

Contribution

It introduces a benchmark for catastrophic forgetting in graph networks, assessing classical continual learning techniques and regularization effects, with a flexible software framework for reproducibility.

Findings

Replay is the most effective forgetting mitigation strategy.

Regularization enhances replay's effectiveness.

Deep graph networks exhibit significant catastrophic forgetting.

Abstract

In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a tangible impact on performances when applied to graph data. To do so, we experiment with a structure-agnostic model and a deep graph network in a robust and controlled environment on three different datasets. The benchmark is complemented by an investigation on the effect of structure-preserving regularization techniques on catastrophic forgetting. We find that replay is the most effective strategy in so far, which also benefits the most from the use of regularization. Our findings suggest interesting future research at the intersection of the continual and graph representation learning fields. Finally, we provide researchers with a flexible software framework to reproduce our results and carry out further experiments.