HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views

TL;DR

HyperGCL introduces a multi-modal hypergraph contrastive learning framework that adaptively constructs and utilizes multiple graph views, leading to superior node classification results by effectively integrating structure and attributes.

Contribution

It proposes a novel hypergraph-based multi-view contrastive learning method with learnable topology augmentation and view-specific encoders, addressing limitations of predefined augmentations.

Findings

Achieves state-of-the-art node classification accuracy.

Effectively preserves task-relevant information through adaptive topology augmentation.

Outperforms existing GCL methods on benchmark datasets.

Abstract

Recent advancements in Graph Contrastive Learning (GCL) have demonstrated remarkable effectiveness in improving graph representations. However, relying on predefined augmentations (e.g., node dropping, edge perturbation, attribute masking) may result in the loss of task-relevant information and a lack of adaptability to diverse input data. Furthermore, the selection of negative samples remains rarely explored. In this paper, we introduce HyperGCL, a novel multimodal GCL framework from a hypergraph perspective. HyperGCL constructs three distinct hypergraph views by jointly utilizing the input graph's structure and attributes, enabling a comprehensive integration of multiple modalities in contrastive learning. A learnable adaptive topology augmentation technique enhances these views by preserving important relations and filtering out noise. View-specific encoders capture essential characteristics from each view, while a network-aware contrastive loss leverages the underlying topology to define positive and negative samples effectively. Extensive experiments on benchmark datasets demonstrate that HyperGCL achieves state-of-the-art node classification performance.