Federated Graph Condensation with Information Bottleneck Principles

arXiv:2405.03911v1 Announce Type: new
Abstract: Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has immediately benefited various graph learning tasks. However, existing graph condensation methods rely on centralized data storage, which is unfeasible for real-world decentralized data distribution, and overlook data holders' privacy-preserving requirements. To bridge the gap, we propose and study the novel problem of federated graph condensation for graph neural networks (GNNs). Specifically, we first propose a …

abstract arxiv centralized data cs.ai cs.lg data data storage decentralized decentralized data distribution graph graph learning however information scale small storage tasks type world