Federated Learning Convergence

Federated learning (FL) convergence research aims to optimize the speed and stability of distributed model training while preserving data privacy. Current efforts focus on improving convergence rates by dynamically adjusting hyperparameters like batch size and aggregation frequency, exploring the use of over-the-air computation and orthogonal sequences for efficient and privacy-preserving communication, and developing hybrid approaches that leverage both client and server data. These advancements are crucial for enabling practical deployment of FL in resource-constrained environments and addressing challenges posed by data heterogeneity and partial client participation, ultimately impacting the scalability and applicability of FL across various domains.

Papers

October 20, 2023

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
Weijie Liu, Xiaoxi Zhang, Jingpu Duan, Carlee Joe-Wong, Zhi Zhou, Xu Chen
Federated Learning Mini Batch Streaming Data Optimal Offline Federated Learning Convergence Incremental Aggregation

June 14, 2023

Differentially Private Wireless Federated Learning Using Orthogonal Sequences
Xizixiang Wei, Tianhao Wang, Ruiquan Huang, Cong Shen, Jing Yang, H. Vincent Poor
Privacy Level Client Level Differential Privacy Federated Learning Convergence

April 10, 2023

Accelerating Hybrid Federated Learning Convergence under Partial Participation
Jieming Bian, Lei Wang, Kun Yang, Cong Shen, Jie Xu
Decentralized Data Machine Learning Paradigm Partial Participation FedCF Method Federated Learning Convergence

October 7, 2022

Depersonalized Federated Learning: Tackling Statistical Heterogeneity by Alternating Stochastic Gradient Descent
Yujie Zhou, Zhidu Li, Tong Tang, Ruyan Wang
Stochastic Gradient Descent Statistical Heterogeneity Federated Learning Convergence

August 15, 2022

Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation
Liang Li, Chenpei Huang, Dian Shi, Hao Wang, Xiangwei Zhou, Minglei Shu, Miao Pan
Energy Policy Research Air Computation Multiple Access Federated Learning Convergence

June 2, 2022

Resource Allocation for Compression-aided Federated Learning with High Distortion Rate
Xuan-Tung Nguyen, Minh-Duong Nguyen, Quoc-Viet Pham, Vinh-Quang Do, Won-Joo Hwang
Federated Learning Model Compression Resource Allocation Distortion Aware Communication Efficiency Federated Learning Convergence Global Convergence Rate

November 15, 2021

On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks
Minsu Kim, Walid Saad, Mohammad Mozaffari, Merouane Debbah
Deep Neural Network Multidimensional Local Precision Rate Energy Policy Research Resource Constrained Device Quantized Neural Network Federated Learning Convergence

Federated Learning Convergence

Papers

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset

Differentially Private Wireless Federated Learning Using Orthogonal Sequences

Accelerating Hybrid Federated Learning Convergence under Partial Participation

Depersonalized Federated Learning: Tackling Statistical Heterogeneity by Alternating Stochastic Gradient Descent

Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation

Resource Allocation for Compression-aided Federated Learning with High Distortion Rate

On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks