Stable one-shot federated learning enables fast model updating at edge devices
One-Shot Federated Model Editing for Device Dynamics at the Edge
Machine LearningArtificial IntelligenceDistributed, Parallel, and Cluster ComputingNetworking and Internet Architecture
Summary
Federated learning normally needs many rounds of communication, which is hard when devices connect and disconnect often, like in cars. The authors designed a stable one-shot federated learning method called F-SOSA that trains models in just one round and can quickly update the model when devices join or leave without retraining from scratch. This method edits models efficiently by removing or adding contributions and keeps model accuracy close to full retraining. Their experiments show it saves time and communication, especially in realistic urban environments.
What this means in practice
- •For edge device engineers: Maintain and update machine learning models on devices that connect intermittently, without costly retraining across multiple communication rounds.
- •For vehicular network operators: Deploy stable federated learning models that adapt quickly to vehicles joining or leaving the network under urban mobility conditions.
Authors
Youming Tao, Weijun Yin, Huanyi Xie, Yanqing Yao, Dongxiao Yu, Xiuzhen Cheng, Di Wang, Falko Dressler
Abstract
Standard federated learning (FL) requires persistent device connectivity across multiple communication rounds, making it unsuitable for dynamic environments such as vehicular networks, where devices frequently join and leave. One-shot FL offers a promising alternative by completing training in a single communication round. However, one-shot FL suffers from model solidification and cannot readily adapt to subsequent client dynamics, including new client contributions and the withdrawal of previous contributions. We therefore consider exact model editing, which removes withdrawn contributions through unlearning or incorporates newly contributed ones through incremental learning without retraining from scratch. We identify that efficient editing fundamentally hinges on learning stability. To this end, we propose F-SOSA, the first stable one-shot FL algorithm that enables rapid and exact model editing. F-SOSA leverages sub-sampling of local models with carefully tuned rate for stable aggregation and performs curvature-aware model fusion to preserve utility. We prove that F-SOSA achieves vanishing training error and reasonably small generalization error bounds. Building on this stability, we further develop two single-round editing algorithms: F-SOSA-U for unlearning and F-SOSA-I for incremental learning. They ensure that the edited model, along with all intermediate algorithmic states, is statistically indistinguishable from retraining while incurring only an expected $O(ρ)$ fraction of its cost, where $ρ$ quantifies stability. Experiments demonstrate that our approach matches retraining performance while reducing cumulative time and communication overhead by at least 36% and 22%, respectively, under realistic urban mobility simulations.