Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks

2025/04/23 by Yanan Zhao, Feng Ji, Zhao, Yanan +15
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2504.16748

openalex publication_date 2025/04/23 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

Abstract

Graph Contrastive Learning (GCL) has recently made progress as an unsupervised graph representation learning paradigm. GCL approaches can be categorized into augmentation-based and augmentation-free methods. The former relies on complex data augmentations, while the latter depends on encoders that can generate distinct views of the same input. Both approaches may require negative samples for training. In this paper, we introduce a novel augmentation-free GCL framework based on graph neural diffusion models. Specifically, we utilize learnable encoders governed by Fractional Differential Equations (FDE). Each FDE is characterized by an order parameter of the differential operator. We demonstrate that varying these parameters allows us to produce learnable encoders that generate diverse views, capturing either local or global information, for contrastive learning. Our model does not require negative samples for training and is applicable to both homophilic and heterophilic datasets. We demonstrate its effectiveness across various datasets, achieving state-of-the-art performance.

Citations

• Distributed-Order Fractional Graph Operating Network
• Community-Invariant Graph Contrastive Learning
• Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
• Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
• Simple and Asymmetric Graph Contrastive Learning without Augmentations
• Graph Neural Convection-Diffusion with Heterophily
• A Fractional Graph Laplacian Approach to Oversmoothing
• A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
• Localized Contrastive Learning on Graphs
• Fractional derivatives: Fourier, elephants, memory effects, viscoelastic materials and anomalous diffusions
• Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
• Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum
• Graph-Coupled Oscillator Networks
• Augmentation-Free Self-Supervised Learning on Graphs
• Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
• Beltrami Flow and Neural Diffusion on Graphs
• Graph Contrastive Learning Automated
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Large-Scale Representation Learning on Graphs via Bootstrapping
• Graph Contrastive Learning with Adaptive Augmentation
• Graph Contrastive Learning with Augmentations
• Deep Graph Contrastive Representation Learning
• Contrastive Multi-View Representation Learning on Graphs
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Geom-GCN: Geometric Graph Convolutional Networks
• Graph Representation Learning via Graphical Mutual Information Maximization
• Multi-scale Attributed Node Embedding
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• Deep Graph Infomax
• Graph Attention Networks
• Inductive Representation Learning on Large Graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• Image-based Recommendations on Styles and Substitutes
• Fast Training of Convolutional Networks through FFTs
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Fractional Dynamics

Related

• Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks
• Augmentation-Free Graph Contrastive Learning with Performance Guarantee
• Diffusion on Graph: Augmentation of Graph Structure for Node Classification
• Graph Representation Learning with Diffusion Generative Models
• Graph Contrastive Learning with Augmentations