Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (27) · 22742-22750
DOI: 10.1609/aaai.v40i27.39436 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xuan Lai und 5 weiteren Autor:innen.
Abstract (Originalsprache)
As an emerging distributed learning paradigm, Federated Learning (FL) facilitates collaborative training among multiple clients without sharing raw data. However, the classic FL still faces significant challenges due to feature/model heterogeneity and catastrophic forgetting, which seriously hinder knowledge transfer and cause the forgetting of previous knowledge. To address these important challenges, we propose FBCL, a novel generalizable heterogeneity-aware Federated features and Basic-matrix Consistency Learning to balance intra-domain discriminability and inter-domain generalization. For feature/model heterogeneity, we align the similarity of feature distribution and construct the high-dimensional basic matrix with irrelevant unlabeled data, thereby overcoming communication barriers and learning generalizable representations while maintaining strict privacy preservation. For catastrophic forgetting during local updating, we introduce constraints in high-dimensional features to retain inter-domain knowledge and then extract accurate knowledge by distilling old models to preserve worthy historical information. Using real-world unlabeled public datasets, extensive experiments validate the superiority of the proposed FBCL, which outperforms the state-of-the-art methods on different scenarios of image classification.
Zitieren
APA
Lai, X., Zhong, L., Lu, T., Zhang, J., Huang, Z., & Chen, Z. (2026). Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(27), 22742-22750. https://doi.org/10.1609/aaai.v40i27.39436
Vancouver
Lai X, Zhong L, Lu T, Zhang J, Huang Z, Chen Z. Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(27):22742-22750. doi:10.1609/aaai.v40i27.39436
BibTeX
@article{Lai2026,
author = {Lai, Xuan and Zhong, Luying and Lu, Tianying and Zhang, Junjie and Huang, Zhiqin and Chen, Zheyi},
title = {Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {27},
pages = {22742--22750},
doi = {10.1609/aaai.v40i27.39436}
}
EUVIMED