Federated Learning

Federated learning (FL) is a decentralized machine learning approach enabling collaborative model training across multiple devices without directly sharing their data, thereby preserving privacy. Current research focuses on addressing challenges like data heterogeneity (non-IID data), communication efficiency (e.g., using scalar updates or spiking neural networks), and robustness to adversarial attacks or concept drift, often employing techniques such as knowledge distillation, James-Stein estimators, and adaptive client selection. FL's significance lies in its potential to unlock the power of massive, distributed datasets for training sophisticated models while adhering to privacy regulations and ethical considerations, with applications spanning healthcare, IoT, and other sensitive domains.

Papers

January 14, 2025

Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
TaeHo Yoon, Sayantan Choudhury, Nicolas Loizou
Federated Learning Timely Communication Game Theoretic Equilibrium State Rational Decision

January 13, 2025

FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation
Zhipeng Deng, Zhe Xu, Tsuyoshi Isshiki, Yefeng Zheng
Federated Learning Semi Supervised Learning Medical Image Segmentation Based Approach Unseen Domain Medical Image Segmentation Task Domain Shift Problem

January 8, 2025

January 7, 2025

A Survey on Federated Learning in Human Sensing
Mohan Li, Martin Gjoreski, Pietro Barbiero, Gašper Slapničar, Mitja Luštrek, Nicholas D. Lane, Marc Langheinrich
Machine Learning Timely Survey Federated Learning Human Sensing Privacy Sensitive

January 5, 2025

Incentive-Compatible Federated Learning with Stackelberg Game Modeling
Simin Javaherian, Bryce Turney, Li Chen, Nian-Feng Tzeng
Federated Learning Stackelberg Game Stackelberg Equilibrium Decentralized Machine

January 3, 2025

Mingling with the Good to Backdoor Federated Learning
Nuno Neves
Federated Learning Backdoor Attack

December 31, 2024

Federated Dropout: Convergence Analysis and Resource Allocation
Sijing Xie, Dingzhu Wen, Xiaonan Liu, Changsheng You, Tharmalingam Ratnarajah, Kaibin Huang
Federated Learning Loss Function Resource Allocation Convergence Analysis Slow Convergence

December 28, 2024

Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance
Li Dong, Yubo Peng, Feibo Jiang, Kezhi Wang, Kun Yang
Federated Learning High Explainability Semantic Communication Industrial Internet Semantic Sensor Network

December 25, 2024

Optimal Federated Learning for Functional Mean Estimation under Heterogeneous Privacy Constraints
Tony Cai, Abhinav Chakraborty, Lasse Vuursteen
Federated Learning Privacy Preserving Privacy Constraint Private Mean Estimation Functional Regression Heterogeneous Privacy

December 23, 2024

FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks
Qian Chen, Xianhao Chen, Kaibin Huang
Federated Learning Capability Evolution Mobile Network Model Convergence Latency Accuracy Inter Satellite Link

December 20, 2024

December 19, 2024

December 18, 2024

Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition
Ruyue Liu, Rong Yin, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong Liu, Can Ma, Weiping Wang
Federated Learning Graph Learning Microbial Decomposition

Federated Learning

Papers

Multiplayer Federated Learning: Reaching Equilibrium with Less Communication

FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation

AutoDFL: A Scalable and Automated Reputation-Aware Decentralized Federated Learning

VerifBFL: Leveraging zk-SNARKs for A Verifiable Blockchained Federated Learning

A Survey on Federated Learning in Human Sensing

Incentive-Compatible Federated Learning with Stackelberg Game Modeling

Mingling with the Good to Backdoor Federated Learning

Federated Dropout: Convergence Analysis and Resource Allocation

Federated Learning with Workload Reduction through Partial Training of Client Models and Entropy-Based Data Selection

Accelerating Energy-Efficient Federated Learning in Cell-Free Networks with Adaptive Quantization

Blockchain-Empowered Cyber-Secure Federated Learning for Trustworthy Edge Computing

Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance

Optimal Federated Learning for Functional Mean Estimation under Heterogeneous Privacy Constraints

FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks

FedGAT: A Privacy-Preserving Federated Approximation Algorithm for Graph Attention Networks

fluke: Federated Learning Utility frameworK for Experimentation and research

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game

LoLaFL: Low-Latency Federated Learning via Forward-only Propagation

FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning

Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition