ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning
This work addresses a bottleneck in graph representation learning for researchers and practitioners by introducing a more informed augmentation scheme, though it is incremental as it builds on existing contrastive learning methods.
The paper tackles the problem of suboptimal performance in graph contrastive learning due to random perturbations that break graph structures, by proposing ENGAGE, an explanation-guided data augmentation method that preserves key graph parts and removes superfluous information, achieving improved results on graph-level and node-level tasks across various real-world graphs.
The recent contrastive learning methods, due to their effectiveness in representation learning, have been widely applied to modeling graph data. Random perturbation is widely used to build contrastive views for graph data, which however, could accidentally break graph structures and lead to suboptimal performance. In addition, graph data is usually highly abstract, so it is hard to extract intuitive meanings and design more informed augmentation schemes. Effective representations should preserve key characteristics in data and abandon superfluous information. In this paper, we propose ENGAGE (ExplaNation Guided data AuGmEntation), where explanation guides the contrastive augmentation process to preserve the key parts in graphs and explore removing superfluous information. Specifically, we design an efficient unsupervised explanation method called smoothed activation map as the indicator of node importance in representation learning. Then, we design two data augmentation schemes on graphs for perturbing structural and feature information, respectively. We also provide justification for the proposed method in the framework of information theories. Experiments of both graph-level and node-level tasks, on various model architectures and on different real-world graphs, are conducted to demonstrate the effectiveness and flexibility of ENGAGE. The code of ENGAGE can be found: https://github.com/sycny/ENGAGE.