Domain-Adaptive Fuzzy Graph Diffusion Networks for Open-Set Cross-Domain Node Classification
IEEE Transactions on Fuzzy Systems · 2026-06 · 34 (6) · 1744-1757
DOI: 10.1109/tfuzz.2026.3672964 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Fuzzy Systems, 2026-06. Verfasst von Sichao Fu und 8 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: General Program of the National Natural Science Foundation of China, Open Project of the Text Computing and Cognitive Intelligence Ministry of Education Engineering Research Center, Guangxi Natural Science Foundation.
Abstract (Originalsprache)
Fuzzy logic-based graph neural networks (FL-GNN) have recently garnered growing attention in node classification, which aims to enhance the ability of GNN in modeling uncertain relationships between nodes. However, existing FL-GNN typically assume that nodes in the source domain (training set) and target domain (test set) follow the identical data distribution and class sets. Real-world scenarios often exhibit significant distribution shifts and target domain even contains classes that were not present in the source domain, termed open-set cross-domain node classification (OSCD-NC), which seriously damages their superior performance. Thus, how to leverage the strong uncertain knowledge representation capacity of FL-GNN to learn a well-defined boundary between seen and unseen classes for improving OSCD-NC performance remains an open and underexplored research problem. In this article, we propose an effective domain-adaptive fuzzy graph diffusion network (DFGDN) for OSCD-NC. Specifically, with the help of a fuzzy adjacency matrix, fuzzy graph diffusion networks are proposed to generate robust fuzzy node representations by adaptively enhancing feature collaboration between low-pass and high-pass graph filters. Then, a peer ($M$+1)-class classifier is introduced to learn a rough class boundary by measuring their class prediction probability difference for target domain. After that, the ($M$+1)-means clustering and decoder modules are simultaneously designed to discover more supervision guidance from target domain for learned class boundary optimization. Finally, we jointly optimize the above modules in an adversarial manner via classification loss, classifier discrepancy loss, and mean squared error loss, which further improves the accuracy of the learned class boundary by pulling seen nodes from the source domain and target domain closer, and pushing unseen nodes away. Extensive experiments on three cross-domain data pairs and various openness rates demonstrate the effectiveness of the proposed DFGDN framework.
Förderung
- General Program of the National Natural Science Foundation of China
- Open Project of the Text Computing and Cognitive Intelligence Ministry of Education Engineering Research Center
- Guangxi Natural Science Foundation
Zitieren
APA
Fu, S., Chen, Y., Peng, S., Ou, W., Ning, L., Zou, B., Peng, Q., Jing, X., & You, X. (2026). Domain-Adaptive Fuzzy Graph Diffusion Networks for Open-Set Cross-Domain Node Classification. IEEE Transactions on Fuzzy Systems, 34(6), 1744-1757. https://doi.org/10.1109/tfuzz.2026.3672964
Vancouver
Fu S, Chen Y, Peng S, Ou W, Ning L, Zou B, et al. Domain-Adaptive Fuzzy Graph Diffusion Networks for Open-Set Cross-Domain Node Classification. IEEE Transactions on Fuzzy Systems. 2026;34(6):1744-1757. doi:10.1109/tfuzz.2026.3672964
BibTeX
@article{Fu2026,
author = {Fu, Sichao and Chen, Yanping and Peng, Songren and Ou, Weihua and Ning, Liangshuo and Zou, Bin and Peng, Qinmu and Jing, Xiao-Yuan and You, Xinge},
title = {Domain-Adaptive Fuzzy Graph Diffusion Networks for Open-Set Cross-Domain Node Classification},
journal = {IEEE Transactions on Fuzzy Systems},
year = {2026},
volume = {34},
number = {6},
pages = {1744--1757},
doi = {10.1109/tfuzz.2026.3672964}
}
EUVIMED