BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 21154-21162
DOI: 10.1609/aaai.v40i25.39259 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Luyang Gai und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Quantization is a pivotal technique for enhancing communication efficiency in Federated Learning (FL). Traditional quantization methods often set uniform intervals, may fail to adequately characterize non-uniform data distributions, thus leading to substantial estimation errors and degrated model performance. Non-uniform quantization can better solve the problem. However, when applied to FL, it would bring additional communication overheads for the alignment of parameter distributions among distributed models. To address this issue, we propose Bisection Interval Quantization (BIQ), a novel non-uniform quantization framework for FL with great communication efficiency. In particular, BIQ works by optimizing the interval selection through recursive bisection among distributed clients without extra parameter communication. For scenarios involving amounts of boundary inputs, we further design Weighted Bisection Interval Quantization (WBIQ), which incorporates maximum likelihood estimation to refine boundary value reconstruction to enhance the estimation quality of boundary inputs. Our theoretical analysis rigorously establishes, for the first time under biased quantization conditions, that both BIQ and WBIQ achieve tighter error bounds and enhanced stability. Extensive experiments validate that both BIQ and WBIQ significantly accelerate the convergence of FL model training when compared to the state-of-the-art quantizers under both convex and non-convex settings.
Zitieren
APA
Gai, L., Yang, S., Ren, X., & Zhou, Z. (2026). BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 21154-21162. https://doi.org/10.1609/aaai.v40i25.39259
Vancouver
Gai L, Yang S, Ren X, Zhou Z. BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):21154-21162. doi:10.1609/aaai.v40i25.39259
BibTeX
@article{Gai2026,
author = {Gai, Luyang and Yang, Shusen and Ren, Xuebin and Zhou, Zihao},
title = {BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {25},
pages = {21154--21162},
doi = {10.1609/aaai.v40i25.39259}
}
EUVIMED