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.
Disentangled Graph Prompting for Out-Of-Distribution Detection
Beijing Key Lab of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Telecommunications（北京邮电大学智能通信软件与多媒体北京市重点实验室）；China Mobile Group Shaanxi Co., Ltd.（中国移动通信集团陕西有限公司）
College of Artificial Intelligence and Automation, Hohai University, China（人工智能与自动化学院，河海大学，中国）；Zhongguancun Laboratory, Beijing, China（中关村实验室，北京，中国）；College of Information Science and Engineering, Hohai University, China（信息科学与工程学院，河海大学，中国）
Improving Out-of-Distribution Detection in Echocardiographic View Classication through Enhancing Semantic Features
Ontact Health（昂泰克健康）；Yonsei University College of Medicine（延世大学医学院）；CONNECT-AI Research Center, Yonsei University College of Medicine（延世大学医学院CONNECT-AI研究中心）；Seoul National University Bundang Hospital（首尔大学盆唐医院）；Severance Cardiovascular Hospital, Yonsei University Health System（延世大学医疗系统世福兰斯心血管医院）
Graph Synthetic Out-of-Distribution Exposure with Large Language Models
University of Southern California（南加州大学）；University of Maryland, College Park（马里兰大学学院 park 分校）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）；Arizona State University（亚利桑那州立大学）
COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
Aalborg University（奥尔堡大学）；ENSTA, Institut Polytechnique de Paris（法国国立高等先进技术学校，巴黎综合理工学院）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
Hong Kong Baptist University（香港浸会大学）；Hefei University of Technology（合肥工业大学）；University of Nottingham（诺丁汉大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；The University of Sydney（悉尼大学）；Sydney AI Centre（悉尼人工智能中心）
Concept Matching with Agent for Out-of-Distribution Detection
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；The Hong Kong Polytechnic University（香港理工大学）；College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）
Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts
University of Cambridge（剑桥大学）；AI Center, UCL（伦敦大学学院人工智能中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ELLIS Institute Tübingen（蒂宾根ELLIS研究所）；Tübingen AI Center（蒂宾根人工智能中心）
ConsPrompt: Exploiting Contrastive Samples for Fewshot Prompt Learning
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Beijing Institute of Technology（北京理工大学）；Southeast Academy of Information Technology（东南信息技术研究院）
LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
Korea University Sejong Campus（韩国大学世宗校区）；Gyeonggi Institute of Education（京畿教育学院）；Indiana University Bloomington（印第安纳大学布卢明顿分校）；Opentutorials；Chosun University（全州大学）；Korea University Korean Studies Center（韩国大学韩学研究中心）
