Adaptive Federated Learning

Adaptive federated learning (AFL) aims to improve the efficiency and robustness of federated learning (FL) by dynamically adjusting model training parameters based on the characteristics of the distributed data and network conditions. Current research focuses on developing adaptive algorithms, such as modifications of Adam and AdaGrad, that optimize learning rates and client selection strategies to address challenges like stragglers, non-IID data, and network heterogeneity. These advancements enhance FL's performance in diverse settings, leading to faster convergence, improved model accuracy, and increased privacy preservation, with significant implications for large-scale distributed machine learning applications.

Papers

October 2, 2024

FLAME: Adaptive and Reactive Concept Drift Mitigation for Federated Learning Deployments
Ioannis Mavromatis, Stefano De Feo, Aftab Khan
Federated Learning Adaptive Importance Internet of Thing Concept Drift Faulty Negative Mitigation Adaptive Federated Learning

March 22, 2024

Adaptive Coded Federated Learning: Privacy Preservation and Straggler Mitigation
Chengxi Li, Ming Xiao, Mikael Skoglund
Differential Privacy Mutual Information Federated Learning Framework Aggregated Gradient Straggler Mitigation Adaptive Federated Learning

March 11, 2024

Adaptive Federated Learning Over the Air
Chenhao Wang, Zihan Chen, Nikolaos Pappas, Howard H. Yang, Tony Q. S. Quek, H. Vincent Poor
Adam Optimizer Convex Loss Adaptive Gradient Method Adaptive Federated Learning Full Matrix AdaGrad Global Gradient

February 15, 2024

Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling
Jiaxiang Geng, Yanzhao Hou, Xiaofeng Tao, Juncheng Wang, Bing Luo
Sampling Technique Client Sampling Adaptive Federated Learning Independent Sampling Heterogeneous Wireless Network Faster Client

October 6, 2023

Utilizing Free Clients in Federated Learning for Focused Model Enhancement
Aditya Narayan Ravi, Ilan Shomorony
Faster Convergence Model Improvement Priority User Adaptive Federated Learning Client Gradient

July 12, 2023

Locally Adaptive Federated Learning
Sohom Mukherjee, Nicolas Loizou, Sebastian U. Stich
Convex Set Federated Averaging Adaptive Federated Learning Local Geometric Information

June 19, 2023

Adaptive Federated Learning with Auto-Tuned Clients
Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis
Stochastic Gradient Descent Machine Learning Framework Step Size Adaptive Federated Learning

March 28, 2023

FedAgg: Adaptive Federated Learning with Aggregated Gradients
Wenhao Yuan, Xuehe Wang
Gradient Descent Learning Rate Decentralized Learning Aggregated Gradient Adaptive Federated Learning Training Epoch

March 27, 2023

Adaptive Federated Learning via New Entropy Approach
Shensheng Zheng, Wenhao Yuan, Xuehe Wang, Lingjie Duan
Learning Rate Decentralized Learning Entropy Model Adaptive Federated Learning

January 23, 2023

Accelerating Fair Federated Learning: Adaptive Federated Adam
Li Ju, Tianru Zhang, Salman Toor, Andreas Hellander
FAIR Federated Learning Fairness Property Adaptive Federated Learning

January 11, 2023

Network Adaptive Federated Learning: Congestion and Lossy Compression
Parikshit Hegde, Gustavo de Veciana, Aryan Mokhtari
Lossy Compression Grid Congestion Adaptive Federated Learning

December 2, 2022

Faster Adaptive Federated Learning
Xidong Wu, Feihu Huang, Zhengmian Hu, Heng Huang
Adaptive Algorithm Federated Learning Algorithm FL Algorithm Adaptive Federated Learning