{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:15:04Z","timestamp":1758672904874,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Heterophilic graph neural networks (GNNs) have gained prominence for their ability to learn effective representations in graphs with diverse, attribute-aware relationships. While existing methods leverage attribute inference during message passing to improve performance, they often struggle with challenging heterophilic graphs. This is due to edge distribution shifts introduced by diverse connection patterns, which blur attribute distinctions and undermine message-passing stability. This paper introduces H\u2082OGNN, a novel framework that reframes edge attribute inference as an out-of-distribution (OOD) detection problem. H\u2082OGNN introduces a simple yet effective symbolic energy regularization approach for OOD learning, ensuring robust classification boundaries between homophilic and heterophilic edge attributes. This design significantly improves the stability and reliability of GNNs across diverse connectivity patterns. Through theoretical analysis, we show that H\u2082OGNN addresses the graph denoising problem by going beyond feature smoothing, offering deeper insights into how precise edge attribute identification boosts model performance. Extensive experiments on nine benchmark datasets demonstrate that H\u2082OGNN not only achieves state-of-the-art performance but also consistently outperforms other heterophilic GNN frameworks, particularly on datasets with high heterophily.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/722","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"6487-6495","source":"Crossref","is-referenced-by-count":0,"title":["All Roads Lead to Rome: Exploring Edge Distribution Shifts for Heterophilic Graph Learning"],"prefix":"10.24963","author":[{"given":"Yi","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University"}]},{"given":"Changqin","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Education, Zhejiang University"},{"name":"Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University"}]},{"given":"Tingyi","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University"}]},{"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University"}]},{"given":"Xiaodi","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computing Mathematics and Engineering, Charles Sturt University"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:34:57Z","timestamp":1758627297000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/722"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/722","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}