Abstract
In multi-cell wireless networks, providing intelligent services via federated learning (FL) becomes more challenging due to multi-level distribution shifts across clients and regions, as well as additional communication delays among edge and cloud servers. To address these issues, we propose SplitOMC, a split learning framework that integrates overlapping-area clients and a multi-exit neural architecture to jointly handle (i) client-preferred, (ii) out-of-preference, and (iii) out-of-region tasks. By strategically leveraging clients in overlapping regions, SplitOMC accelerates training without excessive backhaul communication, while maintaining both personalization and generalization. We theoretically analyze the convergence behavior of the proposed algorithm, ensuring performance stability under heterogeneous data and communication conditions. Extensive experiments on MNIST, CIFAR-10/100, and a real-world Jetson Nano testbed demonstrate that SplitOMC consistently achieves faster training and inference with improved accuracy compared to state-of-the-art methods. In particular, the framework shows robustness in resource-constrained and unstable network environments, highlighting its practical value for next-generation wireless intelligent services.
Funding Information
  • Institute of Information and Communications Technology Planning and Evaluation (IITP-2025-RS-2024-00434743)
  • National Research Foundation of Korea (NRF) grant funded by Korean Government Ministry of Science and ICT (RS-2025-00521295)
  • Korea Health Industry Development Institute (KHIDI) through the Healthcare Technology Research and Development Project funded by the Ministry of Health and Welfare, Republic of Korea (RS-2025-16903040)
  • projects (NSF-IITP CNS-2152646)
  • projects (NSF 2148315)
  • National Science Foundation (CNS-2146171)
  • Defense Advanced Research Projects Agency (D22AP00168)
  • Air Force Office of Scientific Research (FA9550-24-1-0083)