negMIX: Negative Mixup for OOD Generalization in Open-Set Node Classification

2026-03-21

AI Summary

This work addresses the challenges of weak out-of-distribution (OOD) generalization and insufficient intra-class compactness in open-set node classification by proposing negMIX, a novel framework that introduces a negative Mixup strategy tailored for open-set scenarios. By integrating cross-layer graph contrastive learning with a prototype mutual information maximization mechanism, negMIX effectively sharpens the decision boundary between in-distribution (ID) and OOD nodes while enhancing feature consistency and discriminability among nodes of the same class across diverse topological neighborhoods. Extensive experiments demonstrate that negMIX significantly outperforms current state-of-the-art methods across multiple benchmark datasets, achieving substantial improvements in open-set node classification performance.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

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.

Problem

• open-set node classification
• out-of-distribution generalization
• intra-class compactness
• inter-class separability

Innovation

• Negative Mixup
• Open-Set Node Classification
• Out-of-Distribution Generalization
• Cross-Layer Graph Contrastive Learning
• Prototypical Mutual Information