E-CGL: An Efficient Continual Graph Learner

TL;DR

E-CGL introduces an efficient method for continual graph learning that reduces catastrophic forgetting and accelerates training and inference by combining replay strategies with a shared MLP-GCN model.

Contribution

The paper proposes E-CGL, a novel continual graph learning approach that improves efficiency and mitigates forgetting using a shared MLP-GCN model and advanced replay sampling strategies.

Findings

Reduces catastrophic forgetting to an average of -1.1%.

Achieves 15.83x training time acceleration and 4.89x inference time acceleration.

Outperforms nine baseline methods on four datasets.

Abstract

Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual graph learning presents unique challenges that require adaptive and efficient graph learning methods in addition to the problem of catastrophic forgetting. The first challenge arises from the interdependencies between different graph data, where previous graphs can influence new data distributions. The second challenge lies in the efficiency concern when dealing with large graphs. To addresses these two problems, we produce an Efficient Continual Graph Learner (E-CGL) in this paper. We tackle the interdependencies issue by demonstrating the effectiveness of replay strategies and introducing a combined sampling strategy that considers both node importance and diversity. To overcome the limitation of efficiency, E-CGL leverages a simple yet effective MLP model that shares weights with a GCN during training, achieving acceleration by circumventing the computationally expensive message passing process. Our method comprehensively surpasses nine baselines on four graph continual learning datasets under two settings, meanwhile E-CGL largely reduces the catastrophic forgetting problem down to an average of -1.1%. Additionally, E-CGL achieves an average of 15.83x training time acceleration and 4.89x inference time acceleration across the four datasets. These results indicate that E-CGL not only effectively manages the correlation between different graph data during continual training but also enhances the efficiency of continual learning on large graphs. The code is publicly available at https://github.com/aubreygjh/E-CGL.