This repository aggregates minimal implementations of federated learning algorithms built on Flower (PyTorch) for quick start and comparison.
FedAvg/: Minimal implementation of Federated Averaging (FedAvg)FedProto/: Minimal implementation of Federated Prototype Learning (FedProto)FedTGP/: Minimal implementation of Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning (FedTGP)LG-FedAvg/: Minimal implementation of Think Locally, Act Globally (LG-FedAvg)
Refer to each subdirectory README.md for installation and local simulation instructions.
-
Title: Communication-Efficient Learning of Deep Networks from Decentralized Data
Authors: H. Brendan McMahan et al.
Year: 2017
Venue: AISTATS 2017
Link: https://proceedings.mlr.press/v54/mcmahan17a?ref=https://githubhelp.com -
Title: FedProto: Federated Prototype Learning across Heterogeneous Clients
Authors: Yue Tan et al.
Year: 2022
Venue: AAAI-22
Link: https://ojs.aaai.org/index.php/AAAI/article/view/20819 -
Title: FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
Authors: Jianqing Zhang et al.
Year: 2024
Venue: AAAI-24
Link: https://ojs.aaai.org/index.php/AAAI/article/view/29617 -
Title: Think Locally, Act Globally: Federated Learning with Local and Global Representations
Authors: Paul Pu Liang et al.
Year: 2019
Venue: NeurIPS 2019
Link: https://arxiv.org/abs/2001.01523