EXGC: Bridging Efficiency and Explainability in Graph Condensation

TL;DR

EXGC introduces a novel graph condensation method that significantly improves efficiency and explainability by addressing redundancy and convergence issues in large-scale graph data processing.

Contribution

The paper proposes EXGC, combining variational approximation and gradient information bottleneck to enhance efficiency and explainability in graph condensation.

Findings

EXGC outperforms existing methods across eight datasets.

It accelerates convergence using Mean-Field variational approximation.

It effectively reduces parameter redundancy with Gradient Information Bottleneck.

Abstract

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC.