PLGC: Pseudo-Labeled Graph Condensation

TL;DR

PLGC introduces a self-supervised graph condensation method that creates small, synthetic graphs with pseudo-labels, maintaining structural fidelity and robustness in scenarios with limited or noisy labels.

Contribution

It proposes a label-free condensation framework with theoretical guarantees, addressing limitations of supervised methods under label noise and distribution shifts.

Findings

Achieves competitive performance on clean datasets

Shows robustness under label noise

Outperforms supervised methods in noisy environments

Abstract

Large graph datasets make training graph neural networks (GNNs) computationally costly. Graph condensation methods address this by generating small synthetic graphs that approximate the original data. However, existing approaches rely on clean, supervised labels, which limits their reliability when labels are scarce, noisy, or inconsistent. We propose Pseudo-Labeled Graph Condensation (PLGC), a self-supervised framework that constructs latent pseudo-labels from node embeddings and optimizes condensed graphs to match the original graph's structural and feature statistics -- without requiring ground-truth labels. PLGC offers three key contributions: (1) A diagnosis of why supervised condensation fails under label noise and distribution shift. (2) A label-free condensation method that jointly learns latent prototypes and node assignments. (3) Theoretical guarantees showing that pseudo-labels preserve latent structural statistics of the original graph and ensure accurate embedding alignment. Empirically, across node classification and link prediction tasks, PLGC achieves competitive performance with state-of-the-art supervised condensation methods on clean datasets and exhibits substantial robustness under label noise, often outperforming all baselines by a significant margin. Our findings highlight the practical and theoretical advantages of self-supervised graph condensation in noisy or weakly-labeled environments.