GRE^2-MDCL: Graph Representation Embedding Enhanced via Multidimensional Contrastive Learning

TL;DR

GRE2-MDCL introduces a multidimensional contrastive learning framework with a triple network architecture and multi-head attention GNN to enhance graph representations, effectively capturing local and global structures for improved node classification.

Contribution

It proposes a novel multidimensional contrastive loss and a triple network architecture with multi-head attention GNN, advancing graph contrastive learning methods.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Enhances intra-cluster cohesion and inter-cluster separation.

Demonstrates superior performance over baseline GCL models.

Abstract

Graph representation learning has emerged as a powerful tool for preserving graph topology when mapping nodes to vector representations, enabling various downstream tasks such as node classification and community detection. However, most current graph neural network models face the challenge of requiring extensive labeled data, which limits their practical applicability in real-world scenarios where labeled data is scarce. To address this challenge, researchers have explored Graph Contrastive Learning (GCL), which leverages enhanced graph data and contrastive learning techniques. While promising, existing GCL methods often struggle with effectively capturing both local and global graph structures, and balancing the trade-off between nodelevel and graph-level representations. In this work, we propose Graph Representation Embedding Enhanced via Multidimensional Contrastive Learning (GRE2-MDCL). Our model introduces a novel triple network architecture with a multi-head attention GNN as the core. GRE2-MDCL first globally and locally augments the input graph using SVD and LAGNN techniques. It then constructs a multidimensional contrastive loss, incorporating cross-network, cross-view, and neighbor contrast, to optimize the model. Extensive experiments on benchmark datasets Cora, Citeseer, and PubMed demonstrate that GRE2-MDCL achieves state-of-the-art performance, with average accuracies of 82.5%, 72.5%, and 81.6% respectively. Visualizations further show tighter intra-cluster aggregation and clearer inter-cluster boundaries, highlighting the effectiveness of our framework in improving upon baseline GCL models.