Concept-Cognitive Neural Network for Fairness-Aware Maximal Cliques Identification
IEEE Transactions on Emerging Topics in Computing · 2026-04 · 14 (2) · 515-527
DOI: 10.1109/tetc.2026.3681615 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Emerging Topics in Computing, 2026-04. Verfasst von Fei Hao und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Education Humanities and Social Sciences Research Youth Fund Project, Fundamental Research Funds for the Central University.
Abstract (Originalsprache)
To alleviate the scalability bottleneck faced by Formal Concept Analysis (FCA) in mining fairness-aware maximal cliques in attributed social networks, this paper proposes a neuro-symbolic model termed Concept-Cognitive Neural Network (CCNN). Based on the equivalence between fair equiconcept and fairness-aware maximal clique in FCA, CCNN employs deep learning techniques to emulate the concept-generation process of FCA. Specifically, CCNN comprises three core modules: a node embedding encoder, a fair equiconcept upper-bound predictor, and a fair equiconcept generator. Extensive experiments were conducted on multiple random networks and four real-world datasets. The experimental results show that CCNN reduces the runtime on batch data to only 5%–8% of that required by symbolic methods such as RFCRefine, RFCAlter, and FCAMI. The study demonstrates that CCNN offers significant advantages in structural identification and network analysis, thus providing new insights for responsible computational social systems.
Förderung
- National Natural Science Foundation of China
- Ministry of Education Humanities and Social Sciences Research Youth Fund Project
- Fundamental Research Funds for the Central University
- Shaanxi Province Natural Science Basic Research Foundation
Zitieren
APA
Hao, F., Tao, M., Zhang, T., Li, L., & Chen, J. (2026). Concept-Cognitive Neural Network for Fairness-Aware Maximal Cliques Identification. IEEE Transactions on Emerging Topics in Computing, 14(2), 515-527. https://doi.org/10.1109/tetc.2026.3681615
Vancouver
Hao F, Tao M, Zhang T, Li L, Chen J. Concept-Cognitive Neural Network for Fairness-Aware Maximal Cliques Identification. IEEE Transactions on Emerging Topics in Computing. 2026;14(2):515-527. doi:10.1109/tetc.2026.3681615
BibTeX
@article{Hao2026,
author = {Hao, Fei and Tao, Min and Zhang, Tao and Li, Li and Chen, Jianrui},
title = {Concept-Cognitive Neural Network for Fairness-Aware Maximal Cliques Identification},
journal = {IEEE Transactions on Emerging Topics in Computing},
year = {2026},
volume = {14},
number = {2},
pages = {515--527},
doi = {10.1109/tetc.2026.3681615}
}
EUVIMED