Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning

TL;DR

This paper introduces EPA-GRL, a semi-supervised graph learning method that uses explanation-based augmentations to preserve semantics, improving over existing data-perturbation-only approaches.

Contribution

It proposes a novel explanation-preserving augmentation technique for semi-supervised graph representation learning, leveraging graph explanations to generate semantics-preserving augmentations.

Findings

EPA-GRL outperforms state-of-the-art methods on benchmark datasets.

Theoretical analysis confirms the effectiveness of explanation-preserving augmentations.

Extensive experiments demonstrate improved graph representations.

Abstract

Self-supervised graph representation learning (GRL) typically generates paired graph augmentations from each graph to infer similar representations for augmentations of the same graph, but distinguishable representations for different graphs. While effective augmentation requires both semantics-preservation and data-perturbation, most existing GRL methods focus solely on data-perturbation, leading to suboptimal solutions. To fill the gap, in this paper, we propose a novel method, Explanation-Preserving Augmentation (EPA), which leverages graph explanation for semantics-preservation. EPA first uses a small number of labels to train a graph explainer, which infers the subgraphs that explain the graph's label. Then these explanations are used for generating semantics-preserving augmentations for boosting self-supervised GRL. Thus, the entire process, namely EPA-GRL, is semi-supervised. We demonstrate theoretically, using an analytical example, and through extensive experiments on a variety of benchmark datasets, that EPA-GRL outperforms the state-of-the-art (SOTA) GRL methods that use semantics-agnostic augmentations. The code is available at https://github.com/realMoana/EPA-GRL.