Dual-Kernel Graph Community Contrastive Learning
This addresses computational bottlenecks in unsupervised graph learning for researchers and practitioners working with large-scale graph data, representing an incremental improvement over existing GCL methods.
The paper tackles the scalability limitations of Graph Contrastive Learning (GCL) on large graphs by proposing an efficient framework that transforms graphs into compact networks of node sets with a linear-complexity contrastive loss, achieving state-of-the-art performance on sixteen real-world datasets.
Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message passing mechanism of GNN and the quadratic computational complexity of contrastive loss over positive and negative node pairs. To address these issues, we propose an efficient GCL framework that transforms the input graph into a compact network of interconnected node sets while preserving structural information across communities. We firstly introduce a kernelized graph community contrastive loss with linear complexity, enabling effective information transfer among node sets to capture hierarchical structural information of the graph. We then incorporate a knowledge distillation technique into the decoupled GNN architecture to accelerate inference while maintaining strong generalization performance. Extensive experiments on sixteen real-world datasets of varying scales demonstrate that our method outperforms state-of-the-art GCL baselines in both effectiveness and scalability.