Learning Graph Augmentations to Learn Graph Representations

TL;DR

LG2AR is an end-to-end framework that automatically learns effective graph augmentations, significantly improving the quality of graph representations for both node and graph-level tasks across diverse benchmarks.

Contribution

Introduces LG2AR, a novel automatic graph augmentation framework with probabilistic policies and augmentation heads, enhancing generalizable graph representations.

Findings

Achieves state-of-the-art results on 18 out of 20 benchmarks.

Effective for both node and graph-level tasks.

Outperforms previous unsupervised models in various evaluation protocols.

Abstract

Devising augmentations for graph contrastive learning is challenging due to their irregular structure, drastic distribution shifts, and nonequivalent feature spaces across datasets. We introduce LG2AR, Learning Graph Augmentations to Learn Graph Representations, which is an end-to-end automatic graph augmentation framework that helps encoders learn generalizable representations on both node and graph levels. LG2AR consists of a probabilistic policy that learns a distribution over augmentations and a set of probabilistic augmentation heads that learn distributions over augmentation parameters. We show that LG2AR achieves state-of-the-art results on 18 out of 20 graph-level and node-level benchmarks compared to previous unsupervised models under both linear and semi-supervised evaluation protocols. The source code will be released here: https://github.com/kavehhassani/lg2ar