Open Source Federated Learning Framework

Open-source federated learning (FL) frameworks aim to facilitate collaborative model training across decentralized datasets without compromising data privacy. Current research emphasizes improving the efficiency and scalability of these frameworks, evaluating the performance and stability of various FL algorithms (like FedAvg, FedProx, and more advanced variants), and addressing challenges such as open-vocabulary learning and ensuring privacy preservation, particularly in vertical FL settings. This work is crucial for advancing both the theoretical understanding and practical application of FL, enabling wider adoption in diverse fields while mitigating potential vulnerabilities.

Papers

April 9, 2024

pfl-research: simulation framework for accelerating research in Private Federated Learning
Filip Granqvist, Congzheng Song, Áine Cahill, Rogier van Dalen, Martin Pelikan, Yi Sheng Chan, Xiaojun Feng, Natarajan Krishnaswami, Vojta Jina, Mona Chitnis
DH Research Private Federated Learning Simulation Framework Tensorflow Probability Open Source Federated Learning Framework

April 1, 2024

Open-Vocabulary Federated Learning with Multimodal Prototyping
Huimin Zeng, Zhenrui Yue, Dong Wang
Pre Trained Vision Language Model Open Vocabulary Label Space Modal Prototype Open Source Federated Learning Framework

March 26, 2024

Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study
Gustav A. Baumgart, Jaemin Shin, Ali Payani, Myungjin Lee, Ramana Rao Kompella
Federated Learning Performance Evaluation Federated Learning Algorithm Open Source Federated Learning Framework

August 9, 2023

A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks
Weijie Shao, Yuyang Gao, Fu Song, Sen Chen, Lingling Fan, JingZhu He
Machine Learning Model Federated Learning Empirical Study Bug Report Open Source Federated Learning Framework

July 5, 2023

Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectives
Moming Duan, Qinbin Li, Linshan Jiang, Bingsheng He
Timely Survey Federated Learning Vision Paper Technical Report Legal Article Indirect Reciprocity Open Source Federated Learning Framework Federated Learning Platform Decentralized Cooperation

September 25, 2022

On the Stability Analysis of Open Federated Learning Systems
Youbang Sun, Heshan Fernando, Tianyi Chen, Shahin Shahrampour
Federated Learning Stochastic Gradient Stability Analysis Local SGD Real World Benchmark Open Source Federated Learning Framework

July 21, 2022

UniFed: All-In-One Federated Learning Platform to Unify Open-Source Frameworks
Xiaoyuan Liu, Tianneng Shi, Chulin Xie, Qinbin Li, Kangping Hu, Haoyu Kim, Xiaojun Xu, The-Anh Vu-Le, Zhen Huang, Arash Nourian, Bo Li, Dawn Song
Federated Learning Open Source Framework Open Source Federated Learning Framework Federated Learning Platform

July 19, 2022

Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond
Yuzheng Hu, Tianle Cai, Jinyong Shan, Shange Tang, Chaochao Cai, Ethan Song, Bo Li, Dawn Song
Differential Privacy Homomorphic Encryption Logistic Regression Privacy Analysis Mini Batch Gradient Descent Open Source Federated Learning Framework

Open Source Federated Learning Framework

Papers

pfl-research: simulation framework for accelerating research in Private Federated Learning

Open-Vocabulary Federated Learning with Multimodal Prototyping

Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study

A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks

Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectives

On the Stability Analysis of Open Federated Learning Systems

UniFed: All-In-One Federated Learning Platform to Unify Open-Source Frameworks

Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond