![[2602.17342] From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.17342] From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
Summary
The paper presents SIGOOD, a novel framework for improving graph out-of-distribution detection through prompt-driven self-improvement, enhancing reliability in GNN applications.
Why It Matters
As Graph Neural Networks (GNNs) are increasingly deployed in real-world scenarios, ensuring their reliability against out-of-distribution data is crucial. This research introduces an innovative approach that enhances detection capabilities, which is vital for applications in various fields, including AI safety and data science.
Key Takeaways
- SIGOOD integrates continuous self-learning with test-time training for effective OOD detection.
- The framework utilizes prompt-enhanced graphs to amplify OOD signals.
- Energy Preference Optimization (EPO) loss is introduced for optimizing prompts.
- Comprehensive evaluations demonstrate SIGOOD's effectiveness across 21 datasets.
- This approach addresses limitations of traditional one-pass inference methods.
Computer Science > Machine Learning arXiv:2602.17342 (cs) [Submitted on 19 Feb 2026] Title:From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection Authors:Luzhi Wang, Xuanshuo Fu, He Zhang, Chuang Liu, Xiaobao Wang, Hongbo Liu View a PDF of the paper titled From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection, by Luzhi Wang and 5 other authors View PDF HTML (experimental) 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 opt...