Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study

2024-12-23

Trans. Mach. Learn. Res.

AI Summary

Graph neural network (GNN) training on multi-label graph data—such as social and biological networks—is computationally inefficient and resource-intensive; moreover, existing graph compression methods are restricted to single-label settings. Method: This paper pioneers the extension of graph compression to the multi-label regime. We propose a multi-label-aware synthetic graph initialization strategy based on K-Center clustering and an optimization objective using binary cross-entropy loss, thereby relaxing the restrictive single-label assumption. Contribution/Results: We systematically establish the first benchmark for multi-label graph compression. Extensive experiments across eight real-world multi-label datasets demonstrate that our method—GCond augmented with K-Center initialization and binary cross-entropy loss—significantly improves both GNN training efficiency and generalization performance. Our approach establishes a scalable, high-fidelity compression paradigm for large-scale multi-label graph learning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Data Compression
• 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: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

As graph data grows increasingly complicate, training graph neural networks (GNNs) on large-scale datasets presents significant challenges, including computational resource constraints, data redundancy, and transmission inefficiencies. While existing graph condensation techniques have shown promise in addressing these issues, they are predominantly designed for single-label datasets, where each node is associated with a single class label. However, many real-world applications, such as social network analysis and bioinformatics, involve multi-label graph datasets, where one node can have various related labels. To deal with this problem, we extends traditional graph condensation approaches to accommodate multi-label datasets by introducing modifications to synthetic dataset initialization and condensing optimization. Through experiments on eight real-world multi-label graph datasets, we prove the effectiveness of our method. In experiment, the GCond framework, combined with K-Center initialization and binary cross-entropy loss (BCELoss), achieves best performance in general. This benchmark for multi-label graph condensation not only enhances the scalability and efficiency of GNNs for multi-label graph data, but also offering substantial benefits for diverse real-world applications.

Problem

• Extends graph condensation to multi-label datasets
• Addresses computational and efficiency challenges in GNN training
• Enhances scalability for real-world applications like social networks

Innovation

• Extends graph condensation to multi-label datasets
• Uses K-Center initialization and BCELoss optimization
• Enhances GNN scalability for real-world applications