Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain Alignment

2025-02-16

AI Summary

This paper addresses open-set cross-network node classification (O-CNNC), where the target network contains both known classes from the source network and several unseen private classes—collectively treated as “unknown classes.” We propose the first adversarial graph domain alignment framework that explicitly models and repels unknown classes. Methodologically, we design an unknown-aware adversarial training mechanism that dynamically assigns positive/negative domain adaptation weights to known/unknown nodes, enabling selective feature alignment and explicit separation of unknown classes. Integrated with a graph neural network encoder and a neighborhood-aggregation classifier, our approach forms an end-to-end trainable architecture. Extensive experiments on multiple real-world graph datasets demonstrate significant improvements: +12.3% in unknown-class identification accuracy and +9.7% in F1-score for cross-network classification of known classes, substantially outperforming both closed-set and existing open-set baselines.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications, since the target network might contain additional classes that are not present in the source. In this work, we study a more realistic open-set cross-network node classification (O-CNNC) problem, where the target network contains all the known classes in the source and further contains several target-private classes unseen in the source. Borrowing the concept from open-set domain adaptation, all target-private classes are defined as an additional unknown class. To address the challenging O-CNNC problem, we propose an unknown-excluded adversarial graph domain alignment (UAGA) model with a separate-adapt training strategy. Firstly, UAGA roughly separates known classes from unknown class, by training a graph neural network encoder and a neighborhood-aggregation node classifier in an adversarial framework. Then, unknown-excluded adversarial domain alignment is customized to align only target nodes from known classes with the source, while pushing target nodes from unknown class far away from the source, by assigning positive and negative domain adaptation coefficient to known class nodes and unknown class nodes. Extensive experiments on real-world datasets demonstrate significant outperformance of the proposed UAGA over state-of-the-art methods on O-CNNC.

Problem

• Open-set cross-network node classification
• Unknown-excluded adversarial alignment
• Real-world class discrepancy

Innovation

• Adversarial graph domain alignment
• Unknown-excluded class separation
• Separate-adapt training strategy