Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning

TL;DR

This paper introduces a novel self-supervised graph representation learning method called SubGEC, which uses subgraph Gaussian embeddings and optimal transport distances to improve the robustness and effectiveness of graph contrastive learning.

Contribution

The work presents a new subgraph Gaussian embedding module and employs Wasserstein distances for contrastive learning, advancing SSL techniques in graph representation learning.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Enhances robustness of graph contrastive learning.

Highlights importance of distribution in contrastive pairs.

Abstract

Graph Representation Learning (GRL) is a fundamental task in machine learning, aiming to encode high-dimensional graph-structured data into low-dimensional vectors. Self-Supervised Learning (SSL) methods are widely used in GRL because they can avoid expensive human annotation. In this work, we propose a novel Subgraph Gaussian Embedding Contrast (SubGEC) method. Our approach introduces a subgraph Gaussian embedding module, which adaptively maps subgraphs to a structured Gaussian space, ensuring the preservation of input subgraph characteristics while generating subgraphs with a controlled distribution. We then employ optimal transport distances, more precisely the Wasserstein and Gromov-Wasserstein distances, to effectively measure the similarity between subgraphs, enhancing the robustness of the contrastive learning process. Extensive experiments across multiple benchmarks demonstrate that \method~outperforms or presents competitive performance against state-of-the-art approaches. Our findings provide insights into the design of SSL methods for GRL, emphasizing the importance of the distribution of the generated contrastive pairs.