EXGC: Bridging Efficiency and Explainability in Graph Condensation

Published: 23 Jan 2024, Last Modified: 23 May 2024TheWebConf24EveryoneRevisionsBibTeX
Keywords: Graph Neural Networks, Graph Condensation, Model Explainability
TL;DR: We propose an efficient and explainable graph condensation method for boosting the efficiency of current condensation paradigm.
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 **E**fficient and e**X**plainable **G**raph **C**ondensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC’s superiority and relevance. Our code is available at https://anonymous.4open.science/r/EXGC.
Track: Graph Algorithms and Learning for the Web
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 1386
Loading