Bayesian Optimization for Online Bandit Model Partitioning in Split Federated Learning

Federated learning (FL) has been recognized as a promising paradigm to support distributed AI model training among wireless devices (WDs) under the coordination of an edge server (ES) without sharing local datasets. To alleviate computation burden of resource-limited WDs, model partitioning that leverages computing capability at the ES is further integrated into FL, yielding the split (S) FL framework. In this paper, we study online bandit model partitioning for SFL over dynamic wireless networks, aiming to minimize overall energy-latency cost (ELC). Unlike prior works focusing on offline static or online gradientbased model splitting, we consider a practical setting where the analytical expression of ELC function is unavailable, and instead only the function values at queried points are revealed. To tackle such a challenging problem, a novel Bayesian optimization (BO)based approach is put forth by relying on a Gaussian process (GP)-based surrogate model to actively select the model splitting points per round via acquisition function optimization. The training model-specific structural information is incorporated in the kernel design of the GP surrogate to better capture network dynamics. Numerical tests demonstrate that the proposed BObased approach outperforms the contemporary baselines under various practical SFL settings.

• Publication year

  2025

• Venue

  2025 IEEE/CIC International Conference on Communications in China (ICCC)

• Publication date

  2025-08-10

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICCC65529.2025.11148834
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Adaptive Split Learning over Energy-Constrained Wireless Edge Networks

  2024cited by this paper
• AdaptSFL: Adaptive Split Federated Learning in Resource-Constrained Edge Networks

  2024cited by this paper
• Multi-armed bandit approach for mean field game-based resource allocation in NOMA networks

  2024cited by this paper
• Accelerating Split Federated Learning Over Wireless Communication Networks

  2023cited by this paper
• ScaleFL: Resource-Adaptive Federated Learning with Heterogeneous Clients

  2023cited by this paper
• Split Learning Over Wireless Networks: Parallel Design and Resource Management

  2022cited by this paper
• Predictive GAN-Powered Multi-Objective Optimization for Hybrid Federated Split Learning

  2022cited by this paper
• Bayesian Optimization for Online Management in Dynamic Mobile Edge Computing

  2022influential reference
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

  2021cited by this paper
• Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces

  2021cited by this paper
• Structured Projection-free Online Convex Optimization with Multi-point Bandit Feedback

  2021cited by this paper
• SplitFed: When Federated Learning Meets Split Learning

  2020cited by this paper
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence

  2016cited by this paper
• Taking the Human Out of the Loop: A Review of Bayesian Optimization

  2016cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Online convex optimization in the bandit setting: gradient descent without a gradient

  2004cited by this paper
• The Nonstochastic Multiarmed Bandit Problem

  2002cited by this paper

• No citing papers are available for this paper.