RobGC: Towards Robust Graph Condensation

TL;DR

RobGC introduces a robust graph condensation method that enhances GNN training efficiency and noise resilience by jointly denoising training graphs and generating compact, informative graphs for improved real-world applicability.

Contribution

RobGC is a novel plug-and-play approach that incorporates denoising into graph condensation, improving robustness against noisy graph structures during training and inference.

Findings

RobGC significantly improves robustness of GC methods under structural noise.

RobGC enables effective test-time graph denoising for inductive inference.

Experiments demonstrate compatibility and performance gains across various GC methods.

Abstract

Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands, limiting the applicability of GNNs in various scenarios. In response to this challenge, graph condensation (GC) is proposed as a promising acceleration solution, focusing on generating an informative compact graph that enables efficient training of GNNs while retaining performance. Despite the potential to accelerate GNN training, existing GC methods overlook the quality of large training graphs during both the training and inference stages. They indiscriminately emulate the training graph distributions, making the condensed graphs susceptible to noises within the training graph and significantly impeding the application of GC in intricate real-world scenarios. To address this issue, we propose robust graph condensation (RobGC), a plug-and-play approach for GC to extend the robustness and applicability of condensed graphs in noisy graph structure environments. Specifically, RobGC leverages the condensed graph as a feedback signal to guide the denoising process on the original training graph. A label propagation-based alternating optimization strategy is in place for the condensation and denoising processes, contributing to the mutual purification of the condensed graph and training graph. Additionally, as a GC method designed for inductive graph inference, RobGC facilitates test-time graph denoising by leveraging the noise-free condensed graph to calibrate the structure of the test graph. Extensive experiments show that RobGC is compatible with various GC methods, significantly boosting their robustness under different types and levels of graph structural noises.