Open set across network node classification method and apparatus

By employing adversarial training of the graph neural network encoder and neighborhood aggregation node classifier, along with pseudo-label self-training, the challenge of identifying unknown categories in open set cross-network node classification was solved, enabling the accurate classification of known categories and detection of unknown categories in the target network.

CN119939320BActive Publication Date: 2026-05-08HAINAN UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202510126125.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-01-27
Publication Date
2026-05-08
Estimated Expiration
2045-01-27

AI Technical Summary

Technical Problem

Most existing cross-network node classification methods are based on the closed-set assumption, which cannot effectively handle new categories in the target network that do not appear in the source network. Furthermore, the distribution differences between different networks lead to negative migration, making it difficult to accurately identify nodes of unknown categories.

Method used

Adversarial training is performed using a graph neural network encoder and a neighborhood aggregation node classifier. Coarse separation boundaries are constructed through adversarial learning, and precise boundaries are gradually generated through pseudo-label self-training, eliminating adversarial domain alignment for unknown categories.

Benefits of technology

It achieves effective and reliable classification in open set cross-network node classification, improves the ability to identify nodes of unknown categories, and enhances classification accuracy.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses an open set cross-network node classification method and device, relates to the field of machine learning, and designs a framework of separating first and then adapting to a domain. First, an unknown class and a known class are separated by constructing a rough boundary through adversarial learning, and then a pseudo label is allocated to iteratively train a model in a self-training manner, so that a more accurate boundary is gradually generated for separating the known class and the unknown class. Secondly, in the domain adaptation stage, a negative domain adaptation coefficient is allocated to the nodes of the unknown class, and a positive domain adaptation coefficient is allocated to the nodes of the known class, so that the nodes of the known class of the target network are aligned with the source network, and the nodes of the unknown class of the target network are pushed away from the source network, thereby realizing the adversarial domain alignment excluding the unknown class, and further realizing the classification of the open set cross-network node with high accuracy.
Need to check novelty before this filing date? Find Prior Art