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

May 23, 2023

Federated Generalized Category Discovery
Nan Pu, Zhun Zhong, Xinyuan Ji, Nicu Sebe
Contrastive Learning Centralized Learning Generalized Category Discovery Category Discovery

May 18, 2023

Client Selection for Federated Policy Optimization with Environment Heterogeneity
Zhijie Xie, S. H. Song
Reinforcement Learning Policy Gradient Policy Iteration Client Selection Centralized Learning Heterogeneity Environment

March 19, 2023

PFSL: Personalized & Fair Split Learning with Data & Label Privacy for thin clients
Manas Wadhwa, Gagan Raj Gupta, Ashutosh Sahu, Rahul Saini, Vidhi Mittal
Pre Trained Split Learning Personalized Subject Centralized Learning Privacy Label Lightweight Client

February 22, 2023

Towards Decentralized Predictive Quality of Service in Next-Generation Vehicular Networks
Filippo Bragato, Tommaso Lotta, Gianmaria Ventura, Matteo Drago, Federico Mason, Marco Giordani, Michele Zorzi
Reinforcement Learning Decentralized Learning Vehicular Network Service Provider Centralized Learning Quality Prediction

January 24, 2023

Gossiped and Quantized Online Multi-Kernel Learning
Tomas Ortega, Hamid Jafarkhani
Sub Linear Regret Centralized Learning Gossip Algorithm Kernel Learning Online Kernel

January 23, 2023

Backdoor Attacks in Peer-to-Peer Federated Learning
Georgios Syros, Gokberk Yar, Simona Boboila, Cristina Nita-Rotaru, Alina Oprea
Backdoor Attack Centralized Learning Peer to Peer Malicious Node

December 16, 2022

FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks
Weilong Dong, Xinwei Wu, Junzhuo Li, Shuangzhi Wu, Chao Bian, Deyi Xiong
Multi Task Learning Shot Learning Centralized Learning Cross Task Generalization Shot Generalization One Shot Federated Learning Point Wise Weight

December 13, 2022

Robust Split Federated Learning for U-shaped Medical Image Networks
Ziyuan Yang, Yingyu Chen, Huijie Huangfu, Maosong Ran, Hui Wang, Xiaoxiao Li, Yi Zhang
U Net Medical Image Classification Centralized Learning Splitting Algorithm U Shaped Network Split Federated Learning

October 3, 2022

Federated Graph-based Networks with Shared Embedding
Tianyi Yu, Pei Lai, Fei Teng
Graph Based Centralized Learning Based Network Shared Embedding

September 15, 2022

The Cost of Training Machine Learning Models over Distributed Data Sources
Elia Guerra, Francesc Wilhelmi, Marco Miozzo, Paolo Dini
Potential Scalability Hidden CoST Data Sharing Centralized Learning Data Source Training Machine Learning Model

August 24, 2022

Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis
Yawen Wu, Dewen Zeng, Zhepeng Wang, Yi Sheng, Lei Yang, Alaina J. James, Yiyu Shi, Jingtong Hu
Contrastive Learning Masked AutoEncoder Centralized Learning Self Supervised Framework Dermatological Disease Diagnosis Federated Contrastive Learning Dermatological Disease Datasets

August 23, 2022

Application of federated learning techniques for arrhythmia classification using 12-lead ECG signals
Daniel Mauricio Jimenez Gutierrez, Hafiz Muuhammad Hassan, Lorella Landi, Andrea Vitaletti, Ioannis Chatzigiannakis
Application Proficiency Barzilai Borwein Technique Centralized Learning Sensitive Patient 12 Lead

July 15, 2022

Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data
Seyoung Ahn, Soohyeong Kim, Yongseok Kwon, Joohan Park, Jiseung Youn, Sunghyun Cho
Raw Data Performance Improvement Centralized Learning

June 23, 2022

On the Importance and Applicability of Pre-Training for Federated Learning
Hong-You Chen, Cheng-Hao Tu, Ziwei Li, Han-Wei Shen, Wei-Lun Chao
Deep Learning Pre Trained Model Pre Training Importance Aware Centralized Learning Recognition Benchmark Learned Model Applicability Study

May 26, 2022

Mixed Federated Learning: Joint Decentralized and Centralized Learning
Sean Augenstein, Andrew Hard, Lin Ning, Karan Singhal, Satyen Kale, Kurt Partridge, Rajiv Mathews
Federated Learning Decentralized Data Centralized Learning DIstribution Estimation

May 6, 2022

Federated Channel Learning for Intelligent Reflecting Surfaces With Fewer Pilot Signals
Ahmet M. Elbir, Sinem Coleri, Kumar Vijay Mishra
Deep Learning Federated Learning Object Surface Channel Estimation Pilot Study Centralized Learning Intelligent Reflecting Surface

May 5, 2022

General sum stochastic games with networked information flows
Sarah H. Q. Li, Lillian J. Ratliff, Peeyush Kumar
Multi Agent Deep Reinforcement Learning Stochastic Game Centralized Learning Player Interaction

March 9, 2022

Efficient Image Representation Learning with Federated Sampled Softmax
Sagar M. Waghmare, Hang Qi, Huizhong Chen, Mikhail Sirotenko, Tomer Meron
Representation Learning Softmax Function Centralized Learning Softmax Cross Entropy Federated Minimax Optimization

February 10, 2022

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu
Differential Privacy Centralized Learning Generalization Guarantee Private Model Privacy Accuracy Federated Learning Algorithm

February 6, 2022

Applications of Machine Learning in Healthcare and Internet of Things (IOT): A Comprehensive Review
Farid Ghareh Mohammadi, Farzan Shenavarmasouleh, Hamid R. Arabnia
Machine Learning Financial Application Healthcare System Comprehensive Review Internet of Thing Device IOT Technology Centralized Learning Smart Healthcare