LSTM-AdaPQFL: adaptive compression for hierarchical federated learning

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

Energy-Aware Adaptive Quantization and Freezing (EA-AQF), a unified framework that co-optimizes communication and computation, is presented, a unified framework that co-optimizes communication and computation and maintains robust convergence in highly heterogeneous tasks.

CoLT-FL: Compressed Lightweight Transformer-based Federated Learning for Edge Intelligence

The edge devices generate a tremendous amount of sensitive data, which makes the centralized model of training difficult to implement. In this regard, federated learning is introduced, which can perform the task of model training across multiple devices without the need for sharing data, although communication overhead is introduced. The Transformer model is known for its superior learning ability, although the computational cost makes it less applicable for edge devices. Therefore, the need for the proposed CoLT-FL, which is a federated learning framework using a compressed lightweight Transformer model, is introduced. The sparsity-based attention mechanism is introduced, which not only minimizes communication overhead but retains the relevant data as well. The observations made during the experiment indicate that the proposed model performs faster, minimizes latency, and increases the overall accuracy.

GQ-FSL: Green Quantized Federated Split Learning

A green quantized FSL (GQ-FSL) framework that incorporates stochastic quantization for both local collaborative training and wireless transmissions and enables large-scale DNN deployment on resource-constrained devices, achieving superior energy efficiency compared to quantized federated learning and full-precision FSL.

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.

DASFL: Dynamic Adaptive Split Federated Learning for Heterogeneous Clients

Personalized Federated Learning with Low-Rank Pruning-Based Adaptation for Non-IID Data

Personalized Federated Learning (pFL) has emerged as a promising paradigm, while existing approaches face 3 limitations: granularity mismatch, resource waste, and conflict aggregation. This paper presents a Personalized Federated Learning with Low-rank Pruning-based Adaptation (pFedLoPA) framework. Instead of balancing global and local trade-offs, pFedLoPA decouples the model into client-specific cores and globally shared complements. It integrates low-rank adaptation to constrain optimization to a compact subspace, gradient-based pruning to identify personalized parameters, and complementary aggregation to exchange only relevant updates. This enables clients to retain critical knowledge locally while efficiently integrating global knowledge. Extensive experiments on CIFAR-10/100 with multiple network architectures demonstrate that pFedLoPA outperforms state-of-the-art methods in test accuracy (up to 94.31% on CIFAR-10) while reducing communication costs by over 70%.