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

TL;DR

GOODAT is a test-time, data-centric method for detecting out-of-distribution graph samples using a lightweight masker, which learns informative subgraphs without requiring training data or model modifications, outperforming existing methods.

Contribution

This paper introduces GOODAT, a novel test-time OOD detection approach for GNNs that is unsupervised, plug-and-play, and independent of training data, utilizing a graph masker guided by information bottleneck principles.

Findings

GOODAT outperforms state-of-the-art benchmarks on real-world datasets.

It operates independently of training data and GNN modifications.

The method is lightweight and effective for test-time OOD detection.

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. The code is available at Github: https://github.com/Ee1s/GOODAT