Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| 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 |