Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification

2026-03-30

AI Summary

Training graph convolutional networks (GCNs) on large-scale graphs is hindered by substantial computational costs and poor scalability. Existing graph coarsening methods often fall short due to either neglecting multi-granular structural information or incurring high computational complexity. To address these limitations, this work proposes an efficient and scalable granular-ball graph coarsening framework that leverages a linear-time multi-granularity granular-ball algorithm to produce structure-preserving subgraphs. Combined with random sampling and mini-batch training strategies, the approach significantly reduces graph size while maintaining representational fidelity. Extensive experiments on multiple large-scale node classification benchmarks demonstrate that the proposed method achieves superior trade-offs between training efficiency and predictive accuracy compared to state-of-the-art coarsening techniques, thereby validating its effectiveness in enhancing both the scalability and performance of GCNs.

Abstract

Graph Convolutional Network (GCN) is a model that can effectively handle graph data tasks and has been successfully applied. However, for large-scale graph datasets, GCN still faces the challenge of high computational overhead, especially when the number of convolutional layers in the graph is large. Currently, there are many advanced methods that use various sampling techniques or graph coarsening techniques to alleviate the inconvenience caused during training. However, among these methods, some ignore the multi-granularity information in the graph structure, and the time complexity of some coarsening methods is still relatively high. In response to these issues, based on our previous work, in this paper, we propose a new framework called Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification. Specifically, this method first uses a multi-granularity granular-ball graph coarsening algorithm to coarsen the original graph to obtain many subgraphs. The time complexity of this stage is linear and much lower than that of the exiting graph coarsening methods. Then, subgraphs composed of these granular-balls are randomly sampled to form minibatches for training GCN. Our algorithm can adaptively and significantly reduce the scale of the original graph, thereby enhancing the training efficiency and scalability of GCN. Ultimately, the experimental results of node classification on multiple datasets demonstrate that the method proposed in this paper exhibits superior performance. The code is available at https://anonymous.4open.science/r/1-141D/.

Problem

• Graph Convolutional Network
• Graph Coarsening
• Large-scale Graph
• Node Classification
• Computational Overhead

Innovation

• Granular-ball Graph Coarsening
• Multi-granularity
• Scalable GCN
• Linear Time Complexity
• Large-scale Graph Node Classification