Heterogeneous Client

Heterogeneous client federated learning addresses the challenges of collaboratively training machine learning models across devices with vastly different computational capabilities and data distributions. Current research focuses on developing efficient algorithms and model architectures, such as early-exit mechanisms, model splitting, and personalized layers, to accommodate this heterogeneity while maintaining privacy and minimizing communication overhead. These advancements are crucial for enabling large-scale federated learning applications, particularly in resource-constrained environments like mobile and IoT devices, and improving the robustness and accuracy of models trained on diverse data. The ultimate goal is to unlock the potential of decentralized data while overcoming the limitations imposed by client diversity.

Papers

October 30, 2024

Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients
Jabin Koo, Minwoo Jang, Jungseul Ok
Fine Tuning Robust Version Adaptation Concern Low Rank Adaptation Heterogeneous Client

May 27, 2024

Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients
Mohamed Nabih Ali, Alessio Brutti, Daniele Falavigna
Automatic Speech Recognition Dynamic Model Multiple Model Speech Recognition Model Speech Recording Early Exit Heterogeneous Client Partial Model Training

May 23, 2024

Recurrent Early Exits for Federated Learning with Heterogeneous Clients
Royson Lee, Javier Fernandez-Marques, Shell Xu Hu, Da Li, Stefanos Laskaridis, Łukasz Dudziak, Timothy Hospedales, Ferenc Huszár, Nicholas D. Lane
Knowledge Distillation Self Distillation Recurrent Event Recognition Benchmark Early eXit Heterogeneous Client

May 5, 2024

FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients
Zhuohua Li, Maoli Liu, John C. S. Lui
Linear Bandit Heterogeneous Client Contextual Linear Bandit Federated Bandit Conversational Bandit

April 21, 2024

FedTrans: Efficient Federated Learning via Multi-Model Transformation
Yuxuan Zhu, Jiachen Liu, Mosharaf Chowdhury, Fan Lai
Federated Learning Heterogeneous Client Client Model Multi modEl Fusion Model Transformation

March 16, 2024

Federated Learning based on Pruning and Recovery
Chengjie Ma
Edge Pruning Prompt Recovery Heterogeneous Client Asynchronous Learning Training Framework Asynchronous Algorithm

February 29, 2024

Federated Linear Contextual Bandits with Heterogeneous Clients
Ethan Blaser, Chuanhao Li, Hongning Wang
Heterogeneous Client Bandit Model Federated Bandit Federated Linear Contextual Bandit Collaborative Bandit

February 17, 2024

Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients
Xiaolu Wang, Zijian Li, Shi Jin, Jun Zhang
Federated Averaging Asynchronous Federated Learning Heterogeneous Client Linear Speedup FedAvg Converges Stale Global Model

January 17, 2024

Risk-Aware Accelerated Wireless Federated Learning with Heterogeneous Clients
Mohamed Ads, Hesham ElSawy, Hossam S. Hassanein
Federated Learning Model Aggregation Heterogeneous Client

November 19, 2023

FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients
Shangchao Su, Bin Li, Xiangyang Xue
Fine Tuning Foundation Model Real Power Heterogeneous Client Automatic Tuning

October 23, 2023

FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients
Jiyun Shin, Jinhyun Ahn, Honggu Kang, Joonhyuk Kang
Foundation Model Federated Learning Large Model Heterogeneous Client Federated Split Learning

September 26, 2023

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
Zilinghan Li, Pranshu Chaturvedi, Shilan He, Han Chen, Gagandeep Singh, Volodymyr Kindratenko, E. A. Huerta, Kibaek Kim, Ravi Madduri
Heterogeneous Client Heterogeneous Datasets Cross Silo Federated Learning Asynchronous Algorithm Energy Efficient Scheduling Synchronous Algorithm

September 22, 2023

Federated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients
Shourya Bose, Kibaek Kim
Personalized Federated Learning Energy Consumption Heterogeneous Client Short Term Load Forecasting Personalization Layer

August 17, 2023

Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
Xinting Liao, Chaochao Chen, Weiming Liu, Pengyang Zhou, Huabin Zhu, Shuheng Shen, Weiqiang Wang, Mengling Hu, Yanchao Tan, Xiaolin Zheng
Raw Data Decentralized Data Heterogeneous Client Minority Sample Distribution Discrepancy

August 15, 2023

NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients
Honggu Kang, Seohyeon Cha, Jinwoo Shin, Jongmyeong Lee, Joonhyuk Kang
Pre Trained Model Worst Case Heterogeneous Computing Heterogeneous Client System Heterogeneity

April 6, 2023

Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients
Chenrui Wu, Zexi Li, Fangxin Wang, Chao Wu
Label Noise Industrial Disturbing Noise Class Imbalance Heterogeneous Client Noisy Label Learning Safe Learning Mixup Training

December 7, 2022

PaDPaF: Partial Disentanglement with Partially-Federated GANs
Abdulla Jasem Almansoori, Samuel Horváth, Martin Takáč
Generative Model Generative Adversarial Disentanglement Capability Heterogeneous Client Client Model

November 29, 2022

ReAssigner: A Plug-and-Play Virtual Machine Scheduling Intensifier for Heterogeneous Requests
Haochuan Cui, Junjie Sheng, Bo Jin, Yiqiu Hu, Li Su, Lei Zhu, Wenli Zhou, Xiangfeng Wang
Performance Improvement Heterogeneous Client Scheduling Heuristic

November 11, 2022

One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design
Yikai Yan, Chaoyue Niu, Fan Wu, Qinya Li, Shaojie Tang, Chengfei Lyu, Guihai Chen
Image Recognition Model Adaptation Recognition Model Heterogeneous Client Single View Extraction Backbone

November 3, 2022

Client Selection in Federated Learning: Principles, Challenges, and Opportunities
Lei Fu, Huanle Zhang, Ge Gao, Mi Zhang, Xin Liu
Technical Challenge Emerging Opportunity General Principle Client Selection Heterogeneous Client

Heterogeneous Client

Papers

Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients

Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients

FedTrans: Efficient Federated Learning via Multi-Model Transformation

Federated Learning based on Pruning and Recovery

Federated Linear Contextual Bandits with Heterogeneous Clients

Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients

Risk-Aware Accelerated Wireless Federated Learning with Heterogeneous Clients

FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients

FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler

Federated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients

Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data

NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients

Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients

PaDPaF: Partial Disentanglement with Partially-Federated GANs

ReAssigner: A Plug-and-Play Virtual Machine Scheduling Intensifier for Heterogeneous Requests

One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design

Client Selection in Federated Learning: Principles, Challenges, and Opportunities