Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training

TL;DR

This paper introduces a novel graph condensation method using Shock Absorbers and adversarial training to create compact, robust graph representations that preserve essential information and improve GNN performance efficiently.

Contribution

We propose a new graph condensation framework with Shock Absorbers that enhances robustness and efficiency through adversarial training, sharing backward processes without extra overhead.

Findings

Achieved 1.13% to 5.03% accuracy improvements on benchmark datasets.

Added only 0.2% to 2.2% training time overhead, significantly faster than traditional adversarial training.

Validated effectiveness across 8 diverse graph and node classification datasets.

Abstract

In this paper, we study the \textit{graph condensation} problem by compressing the large, complex graph into a concise, synthetic representation that preserves the most essential and discriminative information of structure and features. We seminally propose the concept of Shock Absorber (a type of perturbation) that enhances the robustness and stability of the original graphs against changes in an adversarial training fashion. Concretely, (I) we forcibly match the gradients between pre-selected graph neural networks (GNNs) trained on a synthetic, simplified graph and the original training graph at regularly spaced intervals. (II) Before each update synthetic graph point, a Shock Absorber serves as a gradient attacker to maximize the distance between the synthetic dataset and the original graph by selectively perturbing the parts that are underrepresented or insufficiently informative. We iteratively repeat the above two processes (I and II) in an adversarial training fashion to maintain the highly-informative context without losing correlation with the original dataset. More importantly, our shock absorber and the synthesized graph parallelly share the backward process in a free training manner. Compared to the original adversarial training, it introduces almost no additional time overhead. We validate our framework across 8 datasets (3 graph and 5 node classification datasets) and achieve prominent results: for example, on Cora, Citeseer and Ogbn-Arxiv, we can gain nearly 1.13% to 5.03% improvements compare with SOTA models. Moreover, our algorithm adds only about 0.2% to 2.2% additional time overhead over Flicker, Citeseer and Ogbn-Arxiv. Compared to the general adversarial training, our approach improves time efficiency by nearly 4-fold.