Fortune favors the invariant: Enhancing GNNs’ generalizability with invariant graph learning

Guibin ZHANG, Yiqiao CHEN, Shiyu WANG, Kun WANG, Junfeng Fang

Research output: Contribution to journalArticlespeer-review

Abstract

Generalizable and transferrable graph representation learning endows graph neural networks (GNN) with the ability to extrapolate potential test distributions. Nonetheless, current endeavors recklessly ascribe the demoralizing performance on a single entity (feature or edge) distribution shift and resort to uncontrollable augmentation. By inheriting the philosophy of Invariant graph learning (IGL), which characterizes a full graph as an invariant core subgraph (rationale) and a complementary trivial part (environment), we propose a universal operator termed InMvie to release GNN's out-of-distribution generation potential. The advantages of our proposal can be attributed to two main factors: the comprehensive and customized insight on each local subgraph, and the systematical encapsulation of environmental interventions. Concretely, a rationale miner is designed to find a small subset of the input graph — rationale, which injects the model with feature invariance while filtering out the spurious patterns, i.e., environment. Then, we utilize systematic environment intervention to ensure the out-of-distribution awareness of the model. Our InMvie has been validated through experiments on both synthetic and real-world datasets, proving its superiority in terms of interpretability and generalization ability for node classification over the leading baselines. Copyright © 2024 Elsevier B.V.

Original languageEnglish
Article number111620
JournalKnowledge-Based Systems
Volume292
Early online dateMar 2024
DOIs
Publication statusE-pub ahead of print - Mar 2024

Citation

Zhang, G., Chen, Y., Wang, S., Wang, K., & Fang, J. (2024). Fortune favors the invariant: Enhancing GNNs’ generalizability with invariant graph learning. Knowledge-Based Systems, 292, Article 111620. https://doi.org/10.1016/j.knosys.2024.111620

Keywords

  • PG student publication

Fingerprint

Dive into the research topics of 'Fortune favors the invariant: Enhancing GNNs’ generalizability with invariant graph learning'. Together they form a unique fingerprint.