cs.DCNov 2, 2026

DynSL: Resource-Adaptive Model Training across Heterogeneous Edge Devices

Authors: Boris Radovič, Istemi Ekin Akkus, Marco Canini, Ruichuan Chen, Alice Dethise, Ivica Rimac, Veljko Pejović

Organizations: KAUST · University of Ljubljana, Faculty of Computer and Information Science · Nokia Bell Labs · Jožef Stefan Institute, Department of Computer Systems

Abstract

Training models over data distributed across edge devices presents a trade-off: centralizing data simplifies training but raises privacy and regulatory concerns, while full local training may exceed the devices' compute and memory capacity. Split learning addresses this challenge by partitioning the model between clients and the server, allowing part of the computation to be offloaded. However, existing approaches typically rely on static split configurations or simplified assumptions that fail to capture the heterogeneity and complex dynamics of real deployments. We present DynSL, a framework that dynamically allocates model layers between clients and the server by continuously monitoring system metrics and periodically solving an optimization problem that accounts for client and server computation and communication. When beneficial, the system reconfigures the split, enabling the offloading strategy to adapt to changing device capabilities and system conditions. Extensive experiments on a testbed of 24 heterogeneous edge devices show that DynSL reduces training time by up to ∼ ⁣\sim\!30% over the strongest adaptive baseline and by more than 50% over a suboptimal uniform split, with no loss -- and sometimes a gain -- in accuracy.

Figures & tables

Explore similar work

CardsList
  1. StreamSplit: Continuous Audio Representation Learning via Uncertainty-Guided Adaptive Splitting

    May 26, 2026Minh K. Quan, Pubudu N. PathiranaContrastive LearningAudio Representation Learning

  2. ELSA: Efficient LLM-Centric Split Aggregation for Privacy-Aware Hierarchical Federated Learning over the Network Edge

    Jan 20, 2026Xiaohong Yang, Tong Xie, Minghui Liwang +6Federated Fine-TuningFederated Learning

  3. Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum

    May 10, 2026Akuen Akoi Deng, Eimantas Butkus, Alfreds Lapkovskis +1Efficient Neural Network InferenceEnergy-Efficient ML