Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study
This work addresses computational and efficiency challenges in training graph neural networks for multi-label graph data, which is common in applications like social network analysis and bioinformatics, but it is incremental as it adapts existing techniques to a new data type.
The paper tackles the problem of graph condensation for multi-label datasets, where nodes can have multiple labels, by extending traditional methods with modifications to initialization and optimization, achieving best performance on eight real-world datasets using the GCond framework with K-Center initialization and BCELoss.
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.