From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection

2026-02-19

AI Summary

This work addresses the challenge of effectively detecting out-of-distribution (OOD) graph data in open-world scenarios, where existing graph neural networks often struggle. To this end, the authors propose SIGOOD, a novel framework that introduces, for the first time, a prompt-driven self-improvement mechanism for unsupervised graph OOD detection. During testing, SIGOOD constructs augmented graphs to amplify OOD signals and iteratively refines prompts via an energy preference optimization (EPO) loss function. By dynamically integrating continuous self-learning with test-time training, SIGOOD significantly enhances detection performance. Extensive experiments across 21 real-world datasets demonstrate that the proposed method consistently outperforms current state-of-the-art approaches in graph OOD detection.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, which is critical for ensuring the reliability of Graph Neural Networks (GNNs) when deployed in open-world scenarios. Recent advances in graph OOD detection have focused on test-time training techniques that facilitate OOD detection without accessing potential supervisory information (e.g., training data). However, most of these methods employ a one-pass inference paradigm, which prevents them from progressively correcting erroneous predictions to amplify OOD signals. To this end, we propose a \textbf{S}elf-\textbf{I}mproving \textbf{G}raph \textbf{O}ut-\textbf{o}f-\textbf{D}istribution detector (SIGOOD), which is an unsupervised framework that integrates continuous self-learning with test-time training for effective graph OOD detection. Specifically, SIGOOD generates a prompt to construct a prompt-enhanced graph that amplifies potential OOD signals. To optimize prompts, SIGOOD introduces an Energy Preference Optimization (EPO) loss, which leverages energy variations between the original test graph and the prompt-enhanced graph. By iteratively optimizing the prompt by involving it into the detection model in a self-improving loop, the resulting optimal prompt-enhanced graph is ultimately used for OOD detection. Comprehensive evaluations on 21 real-world datasets confirm the effectiveness and outperformance of our SIGOOD method. The code is at https://github.com/Ee1s/SIGOOD.

Problem

• Graph Out-of-Distribution Detection
• Test-Time Training
• OOD Signal Amplification
• Unsupervised Detection
• Graph Neural Networks

Innovation

• Prompt-Driven Self-Improvement
• Test-Time Training
• Graph OOD Detection
• Energy Preference Optimization
• Prompt-Enhanced Graph