Papers related to Federated Learning in all top venues

[ICLR 2023] "Combating Exacerbated Heterogeneity for Robust Models in Federated Learning"

Multigraph fusion and classification network using graph neural network

Federated Learning (FL) is a collaborative machine learning approach that enables decentralized data processing. Instead of collecting and storing data in a central server, FL trains machine learning models directly on devices or servers where the data resides, enhancing privacy and security.

Library to simulate a distributed learning scenario, with clusters of users that train models minimizing a local cost function, and a server that wants to minimize a global cost function. The aim of the project is to study the tradeoff between local and global accuracy.

[ICLR 2023] "Combating Exacerbated Heterogeneity for Robust Models in Federated Learning"

面向医学图像分类中数据异质性和类不平衡问题的加强联邦学习的设计与分析

This is an implementation of privacy-preserving federated learning for medical image classification. This project demonstrates how multiple medical institutions/nodes/clients can collaborate to train a shared ML model without exchanging sensitive patient data. Built with PyTorch and Flower framework, it supports 3 medical imaging datasets.

The provided Python script generates non-IID (non-identically independently distributed) datasets for use in federated learning simulations. Federated learning often requires data partitions to simulate real-world scenarios where data across devices or clients is unevenly distributed.

Method-reproduction code for Federated Regressive Learning (2024). Includes programmatic scenario generators (S1–S3), baselines, and seeded experiments.