Tensor-Fused Multi-View Graph Contrastive Learning

2024-10-20

arXiv.org

AI Summary

To address insufficient topological feature exploitation and high computational overhead in graph contrastive learning (GCL), this paper proposes TensCL, a novel tensorized contrastive learning framework. TensCL innovatively integrates extended persistent homology (EPH) with multi-view graph augmentation, unifying graph structure and multi-scale topological features via a tensor aggregation-and-compression mechanism. It further enhances robustness through noise injection into EPH computation and reduces computational complexity by decoupling tensor aggregation from transformation. Evaluated on 11 standard graph classification benchmarks, TensCL significantly outperforms 15 state-of-the-art methods on 9 datasets. It achieves superior performance across diverse domains—including molecular property prediction, bioinformatics, and social network analysis—demonstrating its effectiveness in jointly enhancing topological representation capability and computational efficiency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Graph contrastive learning (GCL) has emerged as a promising approach to enhance graph neural networks' (GNNs) ability to learn rich representations from unlabeled graph-structured data. However, current GCL models face challenges with computational demands and limited feature utilization, often relying only on basic graph properties like node degrees and edge attributes. This constrains their capacity to fully capture the complex topological characteristics of real-world phenomena represented by graphs. To address these limitations, we propose Tensor-Fused Multi-View Graph Contrastive Learning (TensorMV-GCL), a novel framework that integrates extended persistent homology (EPH) with GCL representations and facilitates multi-scale feature extraction. Our approach uniquely employs tensor aggregation and compression to fuse information from graph and topological features obtained from multiple augmented views of the same graph. By incorporating tensor concatenation and contraction modules, we reduce computational overhead by separating feature tensor aggregation and transformation. Furthermore, we enhance the quality of learned topological features and model robustness through noise-injected EPH. Experiments on molecular, bioinformatic, and social network datasets demonstrate TensorMV-GCL's superiority, outperforming 15 state-of-the-art methods in graph classification tasks across 9 out of 11 benchmarks while achieving comparable results on the remaining two. The code for this paper is publicly available at https://github.com/CS-SAIL/Tensor-MV-GCL.git.

Problem

• Enhances graph neural networks' representation learning from unlabeled data.
• Addresses computational demands and limited feature utilization in GCL models.
• Captures complex topological characteristics of real-world graph phenomena.

Innovation

• Integrates extended persistent homology with GCL
• Uses tensor aggregation for multi-scale features
• Reduces computational overhead via tensor modules