Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks

TL;DR

This paper introduces an adaptive multi-view graph contrastive learning framework using fractional-order neural diffusion networks, enabling automatic discovery of multi-scale graph representations without manual data augmentation.

Contribution

It proposes a novel fractional-order continuous dynamics approach with learnable diffusion scales for more robust graph embeddings in contrastive learning.

Findings

Outperforms state-of-the-art GCL methods on benchmark datasets.

Produces more robust and expressive node and graph embeddings.

Automatically discovers informative views without manual augmentation.

Abstract

Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective, which limits their ability to capture multi-scale structural patterns. We present an augmentation-free, multi-view GCL framework grounded in fractional-order continuous dynamics. By varying the fractional derivative order $\alpha \in (0,1]$, our encoders produce a continuous spectrum of views: small $\alpha$ yields localized features, while large $\alpha$ induces broader, global aggregation. We treat $\alpha$ as a learnable parameter so the model can adapt diffusion scales to the data and automatically discover informative views. This principled approach generates diverse, complementary representations without manual augmentations. Extensive experiments on standard benchmarks demonstrate that our method produces more robust and expressive embeddings and outperforms state-of-the-art GCL baselines.