GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

Authors

  • Luzhi Wang College of Intelligence and Computing, Tianjin University
  • Dongxiao He College of Intelligence and Computing, Tianjin University
  • He Zhang Faculty of Information Technology, Monash University
  • Yixin Liu Faculty of Information Technology, Monash University
  • Wenjie Wang School of Computing, National University of Singapore
  • Shirui Pan School of Information and Communication Technology, Griffith University
  • Di Jin College of Intelligence and Computing, Tianjin University
  • Tat-Seng Chua School of Computing, National University of Singapore

DOI:

https://doi.org/10.1609/aaai.v38i14.29480

Keywords:

ML: Graph-based Machine Learning, DMKM: Graph Mining, Social Network Analysis & Community

Abstract

Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. While GNNs excel in scenarios where the testing data shares the distribution of their training counterparts (in distribution, ID), they often exhibit incorrect predictions when confronted with samples from an unfamiliar distribution (out-of-distribution, OOD). To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN. Despite their effectiveness, these methods come with heavy training resources and costs, as they need to optimize the GNN-based models on training data. Moreover, their reliance on modifying the original GNNs and accessing training data further restricts their universality. To this end, this paper introduces a method to detect Graph Out-of-Distribution At Test-time (namely GOODAT), a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture. With a lightweight graph masker, GOODAT can learn informative subgraphs from test samples, enabling the capture of distinct graph patterns between OOD and ID samples. To optimize the graph masker, we meticulously design three unsupervised objective functions based on the graph information bottleneck principle, motivating the masker to capture compact yet informative subgraphs for OOD detection. Comprehensive evaluations confirm that our GOODAT method outperforms state-of-the-art benchmarks across a variety of real-world datasets.

Published

2024-03-24

How to Cite

Wang, L., He, D., Zhang, H., Liu, Y., Wang, W., Pan, S., Jin, D., & Chua, T.-S. (2024). GOODAT: Towards Test-Time Graph Out-of-Distribution Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(14), 15537-15545. https://doi.org/10.1609/aaai.v38i14.29480

Issue

Section

AAAI Technical Track on Machine Learning V