Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gong, Junwei, Shen, Xiao, Chen, Zhihao, Pan, Shirui, Wang, Xiao, Zhou, Xi
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.20798
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914413051641856
author Gong, Junwei
Shen, Xiao
Chen, Zhihao
Pan, Shirui
Wang, Xiao
Zhou, Xi
author_facet Gong, Junwei
Shen, Xiao
Chen, Zhihao
Pan, Shirui
Wang, Xiao
Zhou, Xi
contents Open-set node classification (OSNC) allows unlabeled test data to contain novel classes previously unseen in the labeled data. The goal is to classify in-distribution (ID) nodes into corresponding known classes and reject out-of-distribution (OOD) nodes as unknown class. Despite recent notable progress in OSNC, two challenges remain less explored, i.e., how to enhance generalization to OOD nodes, and promote intra-class compactness and inter-class separability. To tackle such challenges, we propose a novel Negative Mixup with Cross-Layer Graph Contrastive Learning (negMIX) model. Firstly, we devise a novel negative Mixup method purposefully crafted for the open-set scenario with theoretical justification, to enhance the model's generalization to OOD nodes and yield clearer ID/OOD boundary. Additionally, a unique cross-layer graph contrastive learning module is developed to maximize the prototypical mutual information between the same class nodes across different topological distance neighborhoods, thereby facilitating intra-class compactness and inter-class separability. Extensive experiments validate significant outperformance of the proposed negMIX over state-of-the-art methods in various scenarios and settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20798
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle negMIX: Negative Mixup for OOD Generalization in Open-Set Node Classification
Gong, Junwei
Shen, Xiao
Chen, Zhihao
Pan, Shirui
Wang, Xiao
Zhou, Xi
Social and Information Networks
Open-set node classification (OSNC) allows unlabeled test data to contain novel classes previously unseen in the labeled data. The goal is to classify in-distribution (ID) nodes into corresponding known classes and reject out-of-distribution (OOD) nodes as unknown class. Despite recent notable progress in OSNC, two challenges remain less explored, i.e., how to enhance generalization to OOD nodes, and promote intra-class compactness and inter-class separability. To tackle such challenges, we propose a novel Negative Mixup with Cross-Layer Graph Contrastive Learning (negMIX) model. Firstly, we devise a novel negative Mixup method purposefully crafted for the open-set scenario with theoretical justification, to enhance the model's generalization to OOD nodes and yield clearer ID/OOD boundary. Additionally, a unique cross-layer graph contrastive learning module is developed to maximize the prototypical mutual information between the same class nodes across different topological distance neighborhoods, thereby facilitating intra-class compactness and inter-class separability. Extensive experiments validate significant outperformance of the proposed negMIX over state-of-the-art methods in various scenarios and settings.
title negMIX: Negative Mixup for OOD Generalization in Open-Set Node Classification
topic Social and Information Networks
url https://arxiv.org/abs/2603.20798