GOODAT: Towards Test-time Graph Out-of-Distribution Detection
Preprint
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/GOODATKeywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Trustworthy Graph Neural Networks: Aspects, Methods, and TrendsProceedings of the IEEE, 2024
- A Data-centric Framework to Endow Graph Neural Networks with Out-Of-Distribution Detection Ability2023
- A survey on fairness-aware recommender systemsInformation Fusion, 2023
- Open-World Lifelong Graph Learning2023
- Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation2023
- Learning on Graphs with Out-of-Distribution Nodes2022
- Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning2022
- Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation2022
- Projective Ranking: A Transferable Evasion Attack Method on Graph Neural Networks2021
- A topological proof of Sklar’s theoremApplied Mathematics Letters, 2013