Semantic Communication-Enhanced Split Federated Learning for Vehicular Networks: Architecture, Challenges, and Case Study

Lu Yu; Zheng Chang; Ying-Chang Liang

cs.LGMar 5, 2026

Semantic Communication-Enhanced Split Federated Learning for Vehicular Networks: Architecture, Challenges, and Case Study

Authors: Lu Yu, Zheng Chang, Ying-Chang Liang

Organizations: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China · Faculty of Information Technology, University of Jyväskylä, FIN-40014 Jyväskylä, Finland · Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China, 611731 Chengdu, China

Abstract

Vehicular edge intelligence (VEI) is vital for future intelligent transportation systems. However, traditional centralized learning in dynamic vehicular networks faces significant communication overhead and privacy risks. Split federated learning (SFL) offers a distributed solution but is often hindered by substantial communication bottlenecks from transmitting high-dimensional intermediate features and can present label privacy concerns. Semantic communication offers a transformative approach to alleviate these communication challenges in SFL by focusing on transmitting only task-relevant information. This paper leverages the advantages of semantic communication in the design of SFL, and presents a case study the semantic communication-enhanced U-Shaped split federated learning (SC-USFL) framework that inherently enhances label privacy by localizing sensitive computations with reduced overhead. It features a dedicated semantic communication module (SCM), with pre-trained and parameter-frozen encoding/decoding units, to efficiently compress and transmit only the task-relevant semantic information over the critical uplink path from vehicular users to the edge server (ES). Furthermore, a network status monitor (NSM) module enables adaptive adjustment of the semantic compression rate in real-time response to fluctuating wireless channel conditions. The SC-USFL framework demonstrates a promising approach for efficiently balancing communication load, preserving privacy, and maintaining learning performance in resource-constrained vehicular environments. Finally, this paper highlights key open research directions to further advance the synergy between semantic communication and SFL in the vehicular network.

Figures & tables

Fig. 1: The workflow of (a) federated learning and (b) split federated learning.

Fig. 2: Comparison of Conventional Bit-Level Communication versus Semantic Effective-Level Communication pipelines.

Figure 3: The SC-USFL framework: overall architecture (left) and SCM pre-training/operation details (right).

Panel of Figure 4 — Figure 4: Performance comparison of SC-USFL with baseline architectures. (a) Test accuracy under AWGN channel. (b) Per-round total latency.

Panel of Figure 5 — Figure 5: Robustness and performance trade-offs of SC-USFL under varying test SNRs and compression ratios for AWGN and Rayleigh channels. Higher CR values (e.g., 1/3) represent milder compression.

Split Federated Learning

Split federated learning divides models between clients and servers to train collaboratively while keeping raw data local.

See all 37 papers

Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation
Apr 27, 2026Huaicheng Li, Junhui Zhao, Haoyu Quan +1Communication-Efficient Distributed Training Low-Rank Adaptation
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China · School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
Encoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs
Sep 28, 2026M. Saeid HaghighiFard, Sinem ColeriHierarchical Federated Learning Intelligent Transportation Systems
Department of Electrical and Electronics Engineering, Koc¸ University, Istanbul, Türkiye
Hierarchical Multi-Task Federated Learning in VANETs
Aug 8, 2026M. Saeid HaghighiFard, Sinem ColeriHierarchical Federated Learning Communication-Efficient Distributed Training
Department of Electrical and Electronics Engineering, Koc University, Istanbul, Turkey

Apr 27, 2026J/K move · Enter open · S save

Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation

Huaicheng Li, Junhui Zhao, Haoyu Quan, Xiaoming Wang

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China · School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China

Communication-Efficient Distributed Training Low-Rank Adaptation Wireless Resource Allocation Federated Learning

Open paper AskPDF arXiv

Federated learning (FL) offers a promising distributed learning paradigm for internet of vehicles (IoV) applications. However, it faces challenges from communication overhead and dynamic environments. Model compression techniques reduce computing and communication burden yet create trade-offs between compression ratios and vehicle participation strategies. In this paper, we propose a lightweight FL algorithm named federated learning with dynamic low-rank adaptation (Fed-DLoRA), which is combined with low-rank adaptation (LoRA) to effectively reduce parameters and communication costs while enhancing training efficiency. The convergence analysis of Fed-DLoRA is conducted through stochastic gradient descent optimization coupled with singular value decomposition. This analysis establishes the theoretical relationships among LoRA rank, vehicular scheduling strategies and the model's convergence characteristics. Building on these insights, we formulate a joint optimization problem aimed at maximizing system performance. To address this problem, we propose an adaptive rank, bandwidth and vehicle selection (ARBVS) algorithm that integrates enumeration with greedy optimization strategies. The algorithm provides efficient rank selection and resource scheduling strategies for each FL communication round, thereby achieving effective performance improvements for the FL system. Experimental results demonstrate that Fed-DLoRA achieves superior performance compared to conventional federated learning approaches, exhibiting enhanced accuracy, faster convergence, and improved communication efficiency.

Abstract

Split Federated Learning

Explore similar work

Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation

Encoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs

Hierarchical Multi-Task Federated Learning in VANETs