Features Based Adaptive Augmentation for Graph Contrastive Learning

TL;DR

This paper proposes Feature Based Adaptive Augmentation (FebAA), a method that selectively preserves influential features during augmentation in graph contrastive learning, improving accuracy across multiple benchmarks.

Contribution

It introduces a novel adaptive augmentation technique that identifies and preserves critical features, enhancing the effectiveness of existing graph contrastive learning methods.

Findings

Improved accuracy of GRACE and BGRL on eight benchmark datasets.

Effective preservation of influential features during augmentation.

Plug-and-play implementation of FebAA enhances existing models.

Abstract

Self-Supervised learning aims to eliminate the need for expensive annotation in graph representation learning, where graph contrastive learning (GCL) is trained with the self-supervision signals containing data-data pairs. These data-data pairs are generated with augmentation employing stochastic functions on the original graph. We argue that some features can be more critical than others depending on the downstream task, and applying stochastic function uniformly, will vandalize the influential features, leading to diminished accuracy. To fix this issue, we introduce a Feature Based Adaptive Augmentation (FebAA) approach, which identifies and preserves potentially influential features and corrupts the remaining ones. We implement FebAA as plug and play layer and use it with state-of-the-art Deep Graph Contrastive Learning (GRACE) and Bootstrapped Graph Latents (BGRL). We successfully improved the accuracy of GRACE and BGRL on eight graph representation learning's benchmark datasets.