Robust Graph Condensation via Classification Complexity Mitigation

TL;DR

This paper introduces MRGC, a novel framework that enhances the robustness of graph condensation by constraining the condensed graph within a low-dimensional data manifold, effectively resisting adversarial attacks.

Contribution

It proposes a manifold-constrained approach to improve the robustness of graph condensation, addressing vulnerabilities to adversarial perturbations.

Findings

MRGC significantly improves robustness against adversarial attacks.

The framework maintains classification complexity reduction.

Extensive experiments validate its effectiveness.

Abstract

Graph condensation (GC) has gained significant attention for its ability to synthesize smaller yet informative graphs. However, existing studies often overlook the robustness of GC in scenarios where the original graph is corrupted. In such cases, we observe that the performance of GC deteriorates significantly, while existing robust graph learning technologies offer only limited effectiveness. Through both empirical investigation and theoretical analysis, we reveal that GC is inherently an intrinsic-dimension-reducing process, synthesizing a condensed graph with lower classification complexity. Although this property is critical for effective GC performance, it remains highly vulnerable to adversarial perturbations. To tackle this vulnerability and improve GC robustness, we adopt the geometry perspective of graph data manifold and propose a novel Manifold-constrained Robust Graph Condensation framework named MRGC. Specifically, we introduce three graph data manifold learning modules that guide the condensed graph to lie within a smooth, low-dimensional manifold with minimal class ambiguity, thereby preserving the classification complexity reduction capability of GC and ensuring robust performance under universal adversarial attacks. Extensive experiments demonstrate the robustness of \ModelName\ across diverse attack scenarios.