Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions

2025/10/07 by Wanli Ni, Hui Tian, Ni, Wanli +9 · 1 citation
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #IoT and Edge/Fog Computing #Modular Robots and Swarm Intelligence #Multiagent Systems (cs.MA) #Optimization and Search Problems #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2510.05713

openalex publication_date 2025/10/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated split learning (FedSL) has emerged as a promising paradigm for enabling collaborative intelligence in industrial Internet of Things (IoT) systems, particularly in smart factories where data privacy, communication efficiency, and device heterogeneity are critical concerns. In this article, we present a comprehensive study of FedSL frameworks tailored for resource-constrained robots in industrial scenarios. We compare synchronous, asynchronous, hierarchical, and heterogeneous FedSL frameworks in terms of workflow, scalability, adaptability, and limitations under dynamic industrial conditions. Furthermore, we systematically categorize token fusion strategies into three paradigms: input-level (pre-fusion), intermediate-level (intra-fusion), and output-level (post-fusion), and summarize their respective strengths in industrial applications. We also provide adaptive optimization techniques to enhance the efficiency and feasibility of FedSL implementation, including model compression, split layer selection, computing frequency allocation, and wireless resource management. Simulation results validate the performance of these frameworks under industrial detection scenarios. Finally, we outline open issues and research directions of FedSL in future smart manufacturing systems.

Citations

• SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding
• Hierarchical Split Federated Learning: Convergence Analysis and System Optimization
• ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issues
• AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks
• Accelerating Split Federated Learning over Wireless Communication Networks
• SplitFed: When Federated Learning Meets Split Learning

Cited by

• Communication-Pipelined Split Federated Learning for Foundation Model Fine-Tuning in UAV Networks

Related

• FedAR: Activity and Resource-Aware Federated Learning Model for Distributed Mobile Robots
• Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things
• Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions
• Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things
• Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art