Partial Participation

Partial participation, where only a subset of available resources or participants contribute to a process, is a crucial challenge across diverse fields like distributed machine learning and computer-assisted surgery. Current research focuses on developing robust algorithms and models that maintain accuracy and efficiency despite incomplete participation, employing techniques such as gradient clipping, dual-branch decoupling in point cloud registration, and adaptive sampling strategies in federated learning. These advancements are vital for improving the scalability, reliability, and practicality of various applications, ranging from large-scale model training to real-time surgical navigation.

Papers

October 4, 2024

Partial-to-Full Registration based on Gradient-SDF for Computer-Assisted Orthopedic Surgery
Tiancheng Li, Peter Walker, Danial Hammoud, Liang Zhao, Shoudong Huang
Surgical Robotic System Preoperative 3D Partial Participation Laparoscopic Liver Pairwise Registration

November 23, 2023

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
Machine Learning Model Variance Reduction Byzantine Robust Client Sampling Gradient Clipping Byzantine Fault Tolerance Partial Participation Byzantine Robust Method

October 18, 2023

DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling
Shiqi Li, Jihua Zhu, Yifan Xie
Point Cloud Registration Overlap Detection Dual Branch Partial Participation

October 9, 2023

On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks
Xin Liu, Wei li, Dazhi Zhan, Yu Pan, Xin Ma, Yu Ding, Zhisong Pan
Neural Network Early Stage Convergence Federated Averaging Deep Linear Two Layer ReLU FedAvg Converges Partial Participation

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

February 20, 2023

TAMUNA: Doubly Accelerated Distributed Optimization with Local Training, Compression, and Partial Participation
Laurent Condat, Ivan Agarský, Grigory Malinovsky, Peter Richtárik
Optimization Purpose Linear Compression Distributed Optimization Robust Algorithm Local Training Local Computation Partial Participation Faster Convergence Speed

June 13, 2022

Anchor Sampling for Federated Learning with Partial Client Participation
Feijie Wu, Song Guo, Zhihao Qu, Shiqi He, Ziming Liu, Jing Gao
Client Participation Partial Participation

May 26, 2022

Combating Client Dropout in Federated Learning via Friend Model Substitution
Heqiang Wang, Jie Xu
Client Participation Substitute Model Partial Participation Client Dropout

March 28, 2022

FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation
Han Wang, Siddartha Marella, James Anderson
Optimization Purpose Federated Prompt Cooperation Primal Dual Algorithm Nonsmooth Regularization Partial Participation

December 4, 2021

Mixed membership distribution-free model
Huan Qing, Jingli Wang
Community Detection Complex Network Modularity Function Distribution Free Weighted Network Partial Participation Mixed Membership Stochastic Block Model

Partial Participation

Papers

Partial-to-Full Registration based on Gradient-SDF for Computer-Assisted Orthopedic Surgery

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences

DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling

On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks

Accelerating Hybrid Federated Learning Convergence under Partial Participation

TAMUNA: Doubly Accelerated Distributed Optimization with Local Training, Compression, and Partial Participation

Anchor Sampling for Federated Learning with Partial Client Participation

Combating Client Dropout in Federated Learning via Friend Model Substitution

FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation

Mixed membership distribution-free model