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

TL;DR

This paper extends graph condensation techniques to multi-label datasets, improving GNN training efficiency and scalability for complex real-world graph data with multiple labels per node.

Contribution

It introduces modifications to traditional graph condensation methods to handle multi-label datasets, validated through experiments on eight real-world datasets.

Findings

GCond with K-Center initialization outperforms other methods

The approach enhances scalability and efficiency of GNNs for multi-label data

Benchmark results demonstrate the effectiveness of the proposed method

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.