Hierarchical Federated Learning Across Heterogeneous Cellular Networks

2019-09-05 · Mehdi Salehi Heydar Abad, Emre Ozfatura, Deniz Gunduz, Ozgur Ercetin

We study collaborative machine learning (ML) across wireless devices, each with its own local dataset. Offloading these datasets to a cloud or an edge server to implement powerful ML solutions is often not feasible due to latency, bandwidth and privacy constraints. Instead, we consider federated edge learning (FEEL), where the devices share local updates on the model parameters rather than their datasets. We consider a heterogeneous cellular network (HCN), where small cell base stations (SBSs) orchestrate FL among the mobile users (MUs) within their cells, and periodically exchange model updates with the macro base station (MBS) for global consensus. We employ gradient sparsification and periodic averaging to increase the communication efficiency of this hierarchical federated learning (FL) framework. We then show using CIFAR-10 dataset that the proposed hierarchical learning solution can significantly reduce the communication latency without sacrificing the model accuracy.

📄 PDF Abstract BibTeX arXiv:1909.02362

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Gradient Sparsification Gradient Sparsification is a technique for distributed training that sparsifies stochastic gradients to reduce the communication cost, with minor increase in the number of…

Data-Heterogeneous Hierarchical Federated Learning with Mobility

2023-06-19 · Tan Chen, Jintao Yan, Yuxuan Sun, Sheng Zhou 외

Federated learning enables distributed training of machine learning (ML) models across multiple devices in a privacy-preserving manner. Hierarchical federated learning (HFL) is further proposed to meet the requirements o…

Federated Learning Privacy Preserving

FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks

2026-06-26 · Emmanuel Rassou, Tomas Gonzalez arxiv

Byzantine-robust federated learning seeks to protect distributed model training from malicious or corrupted clients without requiring access to their private data. FLTrust addresses this challenge by introducing a truste…

Federated Learning

RHFedMTL: Resource-Aware Hierarchical Federated Multi-Task Learning

2023-06-01 · Xingfu Yi, Rongpeng Li, Chenghui Peng, Fei Wang 외

The rapid development of artificial intelligence (AI) over massive applications including Internet-of-things on cellular network raises the concern of technical challenges such as privacy, heterogeneity and resource effi…

Federated Learning Multi-Task Learning

HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation

2022-12-05 · Jun Xia, Yi Zhang, Zhihao Yue, Ming Hu 외

Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centrali…

Diversity Federated Learning Privacy Preserving

Federated Hierarchical Reinforcement Learning for Adaptive Traffic Signal Control

2025-04-07 · Yongjie Fu, Lingyun Zhong, Zifan Li, Xuan Di

Multi-agent reinforcement learning (MARL) has shown promise for adaptive traffic signal control (ATSC), enabling multiple intersections to coordinate signal timings in real time. However, in large-scale settings, MARL fa…

Federated Learning Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning+2