[ICML 2022] "DisPFL: Towards Communication-Efficient Personalized Federated learning via Decentralized Sparse Training"
☆84Jul 12, 2022Updated 3 years ago
Alternatives and similar repositories for DisPFL
Users that are interested in DisPFL are comparing it to the libraries listed below
Sorting:
- Federated Dynamic Sparse Training☆32May 26, 2022Updated 3 years ago
- Decentralized federated learning of deep neural networks on non-iid data☆45Jun 9, 2022Updated 3 years ago
- [ICLR 2021] HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients☆179Feb 27, 2023Updated 3 years ago
- This repository is the official implementation of 'EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Lea…☆14Aug 2, 2022Updated 3 years ago
- [ICML2022] ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training☆23Oct 17, 2022Updated 3 years ago
- FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning☆18Jun 2, 2022Updated 3 years ago
- Understanding Top-k Sparsification in Distributed Deep Learning☆24Nov 15, 2019Updated 6 years ago
- ☆21Nov 10, 2023Updated 2 years ago
- A powerful framework for decentralized federated learning with user-defined communication topology☆12Dec 14, 2021Updated 4 years ago
- ☆12Dec 26, 2024Updated last year
- A repository for LotteryFL re-implementation and experiments☆13Dec 18, 2020Updated 5 years ago
- This repository contains the code for the paper accepted by IJCAI-2022: Adapt to Adaptation: Learning Personalization for Cross-Silo Fede…☆12Sep 2, 2022Updated 3 years ago
- Code accompanying the paper "Decentralized Federated Learning through Proxy Model Sharing"☆84Jun 5, 2023Updated 2 years ago
- DeceFL: A Principled Decentralized Federated Learning Framework☆29Jan 25, 2023Updated 3 years ago
- ☆15Dec 15, 2023Updated 2 years ago
- Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization☆13Jun 21, 2021Updated 4 years ago