AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
An adaptive model compression method, LSTM-AdaPQFL, which dynamically adjusts compression ratios based on predicted bandwidth, gradient information, and training progress, which offers a novel approach to integrating adaptive model compression into hierarchical FL, advancing privacy‐preserving and communication‐efficient distributed 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.
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...
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...
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 s...
Split Federated Learning (SFL) has emerged as a pivotal paradigm for privacy-preserving distributed training on resource-constrained edge devices by partitioning neural networks between clients and a server. A critical design choice in SFL is the split layer, which determines the computation distribution and the semant...
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...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.