Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence
For edge intelligence applications requiring fine-tuning of large vision models on resource-limited devices, this work addresses the communication bottleneck in split federated learning.
ST-SFLora reduces client-side resource consumption in split federated fine-tuning of vision transformers by dynamically selecting semantic tokens and optimizing bandwidth/power allocation, achieving the lowest resource usage among baselines while balancing communication efficiency and model performance.
Deploying large Transformer-based vision models on resource-limited mobile devices at network edge is severely constrained by hardware limitations and dynamic wireless environments. While federated learning (FL) enables collaborative training without sharing raw data, strictly local fine-tuning of such massive models remains computationally prohibitive for edge devices. Split federated learning (SFL) alleviates this burden by offloading deep layers to the edge server, yet it suffers from heavy communication overhead when transmitting high-dimensional activation tokens. To address this bottleneck, we propose ST-SFLora, a semantic token-based split federated LoRA fine-tuning framework. We introduce a new metric, \emph{Semantic Transmission Efficiency} (STE), to balance semantic retention and transmission cost. Based on STE, we formulate a joint resource optimization problem that dynamically determines token selection, uplink bandwidth allocation, and transmit power under latency and energy constraints. The resulting mixed-integer nonconvex problem is efficiently solved via an alternating algorithm. Experiments on multiple benchmarks demonstrate that ST-SFLora achieves the lowest client-side resource consumption among baselines while delivering a favorable trade-off between communication efficiency and model performance.