Centralized Learning

Centralized learning, the traditional approach to training machine learning models, is being challenged by privacy concerns and scalability limitations. Current research focuses on decentralized alternatives like federated learning and its variants, employing techniques such as gradient compression, knowledge distillation, and adaptive client selection to improve efficiency and robustness while preserving data privacy. These advancements are significant because they enable collaborative model training across distributed datasets, unlocking the potential of massive, privacy-sensitive data sources for various applications, including healthcare, IoT, and vehicular networks.

Papers

November 3, 2024

Efficient and Robust Regularized Federated Recommendation
Langming Liu, Wanyu Wang, Xiangyu Zhao, Zijian Zhang, Chunxu Zhang, Shanru Lin, Yiqi Wang, Lixin Zou, Zitao Liu, Xuetao Wei, Hongzhi Yin, Qing Li
High Efficiency Federated Learning Recommender System Centralized Learning Federated Recommendation Recommendation Problem

August 4, 2024

Shaping Rewards, Shaping Routes: On Multi-Agent Deep Q-Networks for Routing in Satellite Constellation Networks
Manuel M. H. Roth, Anupama Hegde, Thomas Delamotte, Andreas Knopp
Multi Agent Deep Reinforcement Learning Reward Shaping Routing Problem Centralized Learning Choice Model Satellite Constellation

July 30, 2024

The Entrapment Problem in Random Walk Decentralized Learning
Zonghong Liu, Salim El Rouayheb, Matthew Dwyer
Decentralized Learning Importance Sampling Random Walk Centralized Learning Decentralized SGD

July 24, 2024

Federated Automatic Latent Variable Selection in Multi-output Gaussian Processes
Jingyi Gao, Seokhyun Chung
Centralized Learning Multi Output Gaussian Process Independent Latent

July 17, 2024

Proximity-based Self-Federated Learning
Davide Domini, Gianluca Aguzzi, Nicolas Farabegoli, Mirko Viroli, Lukas Esterle
Edge Computing Centralized Learning Federated Self Supervised Learning Large Network

June 7, 2024

When Swarm Learning meets energy series data: A decentralized collaborative learning design based on blockchain
Lei Xu, Yulong Chen, Yuntian Chen, Longfeng Nie, Xuetao Wei, Liang Xue, Dongxiao Zhang
Decentralized Learning Blockchain Based Platform Smart Contract Centralized Learning Consensus Mechanism Swarm Learning

May 28, 2024

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
Thanh Trung Huynh, Trong Bang Nguyen, Phi Le Nguyen, Thanh Tam Nguyen, Matthias Weidlich, Quoc Viet Hung Nguyen, Karl Aberer
Unlearning Framework Centralized Learning Unlearned Model Federated Unlearning Model Resilience Fast FedUL

May 22, 2024

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
Huiwen Wu, Xiaohan Li, Deyi Zhang, Xiaogang Xu, Jiafei Wu, Puning Zhao, Zhe Liu
Gradient Compression Centralized Learning Federated Variational Federated Tuning CG FedLLM

April 1, 2024

Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm
Zhonghao Lyu, Yuchen Li, Guangxu Zhu, Jie Xu, H. Vincent Poor, Shuguang Cui
Parameter Efficient Fine Tuning Joint Framework Centralized Learning Edge Learning Resource Management Edge Server

March 18, 2024

KnFu: Effective Knowledge Fusion
S. Jamal Seyedmohammadi, S. Kawa Atapour, Jamshid Abouei, Arash Mohammadi
Knowledge Distillation Centralized Learning Knowledge Fusion Federated Distillation

February 20, 2024

Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness
Nikola Pavlovic, Sudeep Salgia, Qing Zhao
Kernel Hilbert Space Centralized Learning Uniform Sampling Sparse Approximation Order Optimal Regret Kernel Bandit Distributed Stochastic

January 13, 2024

FedDriveScore: Federated Scoring Driving Behavior with a Mixture of Metric Distributions
Lin Lu
Mixture Component Federated Edge Learning Centralized Learning Vehicle Road Cloud Metric Distribution

December 19, 2023

Decentralised and collaborative machine learning framework for IoT
Martín González-Soto, Rebeca P. Díaz-Redondo, Manuel Fernández-Veiga, Bruno Rodríguez-Castro, Ana Fernández-Vilas
Machine Learning Incremental Learning IOT Technology Centralized Learning Collaborative Machine Learning Randomized Communication

December 18, 2023

Online Vertical Federated Learning for Cooperative Spectrum Sensing
Heqiang Wang, Jie Xu
Vertical Federated Learning Centralized Learning Spectrum Sensing Spectrum Management Spectrum Utilization

October 27, 2023

Weighted Sampled Split Learning (WSSL): Balancing Privacy, Robustness, and Fairness in Distributed Learning Environments
Manish Osti, Aashray Thakuri, Basheer Qolomany, Aos Mulahuwaish
Machine Learning Native Robustness Split Learning Centralized Learning Weighted Sampling

October 4, 2023

Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework
Jingheng Zheng, Wanli Ni, Hui Tian, Deniz Gunduz, Tony Q. S. Quek, Zhu Han
Optimization Purpose Semi Supervised Convergence Analysis Adaptive Beamforming Centralized Learning Hybrid Machine Learning Non Orthogonal Multiple Access

July 28, 2023

The Applicability of Federated Learning to Official Statistics
Joshua Stock, Oliver Hauke, Julius Weißmann, Hannes Federrath
Centralized Learning Applicability Study Model Benchmark

July 16, 2023

DynamicFL: Balancing Communication Dynamics and Client Manipulation for Federated Learning
Bocheng Chen, Nikolay Ivanov, Guangjing Wang, Qiben Yan
Dynamic Network Centralized Learning Manipulation Strategy

June 19, 2023

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation
Jingwen Guo, Hong Liu, Shitong Sun, Tianyu Guo, Min Zhang, Chenyang Si
Knowledge Distillation Skeleton Based Action Recognition Federated Prompt Cooperation Centralized Learning Adaptive Structure

June 6, 2023

Guiding The Last Layer in Federated Learning with Pre-Trained Models
Gwen Legate, Nicolas Bernier, Lucas Caccia, Edouard Oyallon, Eugene Belilovsky
Pre Trained Model Centralized Learning Last Layer Transferable Visual

Centralized Learning

Papers

Efficient and Robust Regularized Federated Recommendation

Shaping Rewards, Shaping Routes: On Multi-Agent Deep Q-Networks for Routing in Satellite Constellation Networks

The Entrapment Problem in Random Walk Decentralized Learning

Federated Automatic Latent Variable Selection in Multi-output Gaussian Processes

Proximity-based Self-Federated Learning

When Swarm Learning meets energy series data: A decentralized collaborative learning design based on blockchain

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models

Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm

KnFu: Effective Knowledge Fusion

Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness

FedDriveScore: Federated Scoring Driving Behavior with a Mixture of Metric Distributions

Decentralised and collaborative machine learning framework for IoT

Online Vertical Federated Learning for Cooperative Spectrum Sensing

Weighted Sampled Split Learning (WSSL): Balancing Privacy, Robustness, and Fairness in Distributed Learning Environments

Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework

The Applicability of Federated Learning to Official Statistics

DynamicFL: Balancing Communication Dynamics and Client Manipulation for Federated Learning

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

Guiding The Last Layer in Federated Learning with Pre-Trained Models