GQ-FSL: Green Quantized Federated Split Learning Framework for Wireless Edge Networks

Asymmetric Partial Model Transmission for Federated Edge Learning

Federated learning (FL) applications normally employ large deep learning (DL) models, resulting in excessive communication overhead in the deployment of FL over resource-constraint mobile edge networks. To achieve better scalability for DL-based FL, we capitalize on both the asymmetric nature of mobile networks and the distinct effects of partial transmissions on FL training for the global and local models. We propose Fed-DynAmal, an FL framework that decreases the number of parameters transmitted in the uplink (clients-to-server) while concurrently achieving better model performance. The underlying idea is that each selected client sends a partial DL model to the server by omitting several sub-blocks from the trained local model. Crucially, we drop the assumption that transmitted local models can still be used for inference, thereby allowing for greater model variability. At the server, we introduce amalgamation, a process to merge different partial local models into an inference-viable full model. Essentially, amalgamation is a bridge for performing aggregation at the sub-block level. Interestingly, as the key takeaway, communication efficiency versus model performance is not necessarily a trade-off in FL: Our extensive experiments show that Fed-DynAmal can effectively improve communication efficiency while still concurrently achieving higher accuracy and enhanced robustness.

FSLT: A Federated Split Learning Testbed for 5G Wireless Networks

With the emergence of next-generation communication technologies, the integration of AI into next-generation wireless networks is becoming an important step toward achieving distributed intelligence. Different distributed learning frameworks, such as federated learning (FL) and split learning (SL), enable collaborative model training by distributing computation between user equipment (UEs) and edge servers. However, FL suffers from high communication overhead due to frequent model synchronization, while SL introduces significant latency at the split layer and is sensitive to channel conditions. The effects of wireless channel dynamics on distributed learning performance and the communication-computation trade-offs across different split layers remain insufficiently studied in practical scenarios. In this work, we present a Federated Split Learning Testbed (FSLT) over 5G wireless networks that integrates FL and SL within an OpenAirInterface (OAI) software-defined radio platform. FSLT enables empirical evaluation of learning–communication trade-offs under realistic wireless conditions. The framework distributes neural network layers between UEs and edge servers, allowing investigation of channel variability, latency, and split-point selection on training performance. Experiments on an avatar skeleton extraction task demonstrate that FSLT reduces communication load by 5%-8% compared with FL and achieves faster convergence than SL under dynamic channel conditions. These results provide practical insights into optimizing distributed learning over 5G edge systems and pave the way toward AI-native 6G networks.

When Split Federated Learning Meets Prototype Learning: A Communication-Efficient Approach in Wireless Networks

Nowadays, split federated learning (SFL) has emerged as an effective paradigm for enabling privacy-preserving collaborative intelligence across heterogeneous devices with limited computation. However, SFL incurs significant communication overhead in wireless networks due to the uplink transmission of high-dimensional smashed data, which degrades network efficiency. To mitigate the communication bottleneck, we propose a prototype-based SFL framework ProtoSFL. Specifically, each selected client computes local prototypes for observed classes and uploads them to the server. Based on the received prototypes, the server derives global prototypes and optimizes a weighted objective that combines classification loss with prototype alignment loss. The server then updates the model accordingly and returns personalized prototype gradients to the clients. Simulation results verify the effectiveness of ProtoSFL in reducing communication overhead, achieving a substantial reduction in uplink communication, while maintaining competitive testing accuracy under various heterogeneous data settings compared with SFL baselines.

EA-AQF: energy aware adaptive quantization and freezing in federated learning

Communication-Efficient Over-the-Air Federated Learning via Lightweight Gradient Compression

Integrating over-the-air computations into the model aggregation process of federated learning (FL) offers a promising solution to mitigate the communication bottleneck in FL model training. In this approach, all the clients modulate their intermediate parameters, such as gradients, onto the same set of orthogonal waveforms and transmit the resulting signals to the edge server simultaneously. Capitalizing on the superposition property of the radio channel, the server can extract an automatically aggregated global gradient from the received radio signal. However, the limited number of orthogonal waveforms imposes a constraint on the dimensionality of transmittable updates, hindering the adoption of more advanced, but high-dimensional models. In light of this challenge, we propose OFLight, a lightweight, yet effective, gradient compression algorithm tailored for OTA-FL systems. Specifically, in each communication round, the edge server constructs a low-rank projection matrix based on the received gradient matrix from the previous round (initialized with an independent and identically distributed standard normal matrix in the first round) and broadcasts it, along with the global model, to all clients in the system. Based on this matrix, every client projects its locally updated gradient matrix into a low-dimensional subspace through a linear operation. The clients upload only their compressed gradients via OTA computations, and the edge server can perform a linear decompression on the received signal, retrieving the original gradient dimension. Moreover, an error feedback mechanism is incorporated to compensate for the approximation error under aggressive compression. We derive analytical expressions for the convergence rate of both convex and non-convex loss functions, quantitatively demonstrating the effect of OFLight on the OTA-FL training efficiency. We also conduct extensive experiments to corroborate the efficacy of the proposed method.

Energy-Aware Federated Distillation via Quantum-Driven Task Offloading in LEO Satellite Networks

Low earth orbit (LEO) satellite networks have emerged as a key enabler for delivering real-time and global services to distributed terrestrial nodes, particularly in remote regions. To preserve data privacy, federated learning (FL) provides a decentralized framework for advancing artificial intelligence (AI) in complex tasks. However, the efficiency of FL is constrained by high and imbalanced energy consumption, which limits its practical deployment. To address these challenges, an energy-aware FL framework that integrates knowledge distillation (KD) with task offloading is proposed, where KD is performed at both the FL server and client devices or direct-connected satellites using public datasets. The energy consumption balancing problem is formulated as a quadratic unconstrained binary optimization (QUBO) model. To achieve computational efficiency and parallelism, the quantum approximate optimization algorithm (QAOA) is employed to solve the problem with both the mixing and cost Hamiltonians derived and the corresponding quantum circuit designed. In a FL framework over a LEO satellite network comprising 40 satellites and 10 FL clients, the proposed method reduces energy consumption by approximately 26.4%, achieves improved energy balance with a weighted variance of approximately 4.93 and maintains high accuracy of 0.95 in a vehicle classification task, compared with the traditional FL method.