AS-GCL: Asymmetric Spectral Augmentation on Graph Contrastive Learning

TL;DR

AS-GCL introduces an innovative spectral augmentation technique for graph contrastive learning, enhancing robustness and generalization by leveraging asymmetric spectral encoders and a novel loss function, outperforming existing methods.

Contribution

The paper presents the first use of asymmetric spectral encoders in GCL, incorporating spectral-based augmentation and a new loss to improve graph representation learning.

Findings

Outperforms existing GCL methods on eight benchmark datasets

Enhances structural invariance and noise reduction through spectral augmentation

Improves generalization with a novel upper-bound contrastive loss

Abstract

Graph Contrastive Learning (GCL) has emerged as the foremost approach for self-supervised learning on graph-structured data. GCL reduces reliance on labeled data by learning robust representations from various augmented views. However, existing GCL methods typically depend on consistent stochastic augmentations, which overlook their impact on the intrinsic structure of the spectral domain, thereby limiting the model's ability to generalize effectively. To address these limitations, we propose a novel paradigm called AS-GCL that incorporates asymmetric spectral augmentation for graph contrastive learning. A typical GCL framework consists of three key components: graph data augmentation, view encoding, and contrastive loss. Our method introduces significant enhancements to each of these components. Specifically, for data augmentation, we apply spectral-based augmentation to minimize spectral variations, strengthen structural invariance, and reduce noise. With respect to encoding, we employ parameter-sharing encoders with distinct diffusion operators to generate diverse, noise-resistant graph views. For contrastive loss, we introduce an upper-bound loss function that promotes generalization by maintaining a balanced distribution of intra- and inter-class distance. To our knowledge, we are the first to encode augmentation views of the spectral domain using asymmetric encoders. Extensive experiments on eight benchmark datasets across various node-level tasks demonstrate the advantages of the proposed method.