arXiv cs.AI· Quan Minh Nguyen, Hoang M. Ngo, Bhakti Chowkwale, Yasaman Keshtkarjahromi, My T. Thai·· 3 小时前AI 评分33
FedFiOT：基于 Fisher 加权最优传输的一次性与少轮次联邦学习模型合并方法
FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning
AI 导读
FedFiOT 是一种面向一次性和少轮次联邦学习的 Fisher 加权最优传输模型合并框架，利用 Fisher 信息量化参数重要性并指导神经元对齐与模型聚合，通过交替最小化共享目标函数联合优化神经元对应关系和全局模型参数。理论上该方法单调递减逐层合并目标，并给出刻画客户端异质性和非均匀 Fisher 影响的平稳性界；多数据集实验显示其在两种设置下均稳定优于基线。
正文 · 原文
Abstract:One-shot and few-round federated learning (FL) reduce communication burden by constructing a global model within one or a few communication rounds, but often achieve lower performance than conventional multi-round FL. Without frequent synchronization, client models may drift apart, causing neurons that learn similar features to occupy different positions across clients. At the same time, local data heterogeneity can cause corresponding parameters to differ in their importance to each client's predictions. Together, these challenges cause direct averaging to combine mismatched neurons and assign equal weight to parameters despite differences in their importance. We propose FedFiOT, a Fisher-weighted optimal transport framework for one-shot and few-round FL that leverages Fisher information to quantify parameter importance and guide neuron alignment and model aggregation. FedFiOT jointly optimizes neuron correspondences and global model parameters through alternating minimization of a shared Fisher-weighted objective. Theoretically, we show that FedFiOT's optimization procedure monotonically decreases the layer-wise merging objective and establish a stationarity bound that quantifies the effects of client heterogeneity and nonuniform Fisher this http URL across multiple datasets demonstrate consistent improvements over competing baselines in both one-shot and few-round federated learning settings.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06783 [cs.LG] |
| (or arXiv:2611.06783v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06783 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Quan Nguyen [view email]
[v1]
Wed, 4 Nov 2026 16:56:10 UTC (535 KB)
来源：arXiv cs.AI · arxiv.org