PyramidSFL: Resource-aware Split Federated Learning via Adaptive Model Splitting

Split Federated Learning (SFL) has emerged as a promising distributed learning paradigm that offloads part of the on-device training workload to a resource-rich server while keeping raw data at the edge. However, its effectiveness is often challenged by heterogeneity in both data silos and client resources, which jointly undermine model performance and training efficiency. This paper proposes PyramidSFL, a system-efficient Stacked-Activation SFL (SA-SFL) framework that dynamically partitions the model between clients and the server according to each client's communication and computation profile. To counteract the accuracy drop caused by dynamic model splitting, PyramidSFL combines a warm-up strategy that stabilizes early global optimization with a weight-shrinking mechanism that reduces cross-layer update inconsistency. This enables efficient training without sacrificing model quality, leading to a better time-to-accuracy performance. Extensive experiments on real-world benchmarks show that PyramidSFL consistently improves the accuracy-latency trade-off over existing FL and SFL baselines, improving global model accuracy by up to 15.53% under the same wall-clock budget and reducing convergence latency by up to 72.86%. Its gains become more significant under tighter client resource constraints and deeper task models, highlighting its effectiveness for heterogeneous and resource-constrained edge training.