ditto
Federated Learning Framework
A framework for personalized federated learning to balance fairness and robustness in decentralized machine learning systems.
Ditto: Fair and Robust Federated Learning Through Personalization (ICML '21)
137 stars
2 watching
30 forks
Language: Python
last commit: over 2 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 diogenes0319/fedmd_clean | An implementation of a heterogenous federated learning framework using model distillation. | 149 |
 rong-dai/dispfl | An implementation of a personalized federated learning framework with decentralized sparse training and peer-to-peer communication protocol. | 68 |
 ibm/federated-learning-lib | A framework for collaborative distributed machine learning in enterprise environments. | 499 |
 desternylin/perfed | An implementation of various federated learning algorithms with a focus on communication efficiency, robustness, and fairness. | 15 |
 jiayunz/fedalign | Develops an alignment framework for federated learning with non-identical client class sets | 4 |
 cuis15/fcfl | An implementation of Fair and Consistent Federated Learning using Python. | 20 |
 mediabrain-sjtu/fedgela | Federated learning algorithm designed to handle partially class-disjoint data by utilizing bilateral curation and Dirichlet partitioning. | 10 |
 fangxiuwen/robust_fl | An implementation of a robust federated learning framework for handling noisy and heterogeneous clients in machine learning. | 41 |
 yutong-dai/fednh | An implementation of a federated learning framework for handling data heterogeneity in decentralized settings | 38 |
 git-disl/scale-fl | An adaptive federated learning framework for heterogeneous clients with resource constraints. | 29 |
 bytedance/feddecorr | Provides an implementation of various heterogeneous federated learning methods and datasets to mitigate dimensional collapse in distributed machine learning | 63 |
 omarfoq/fedem | Develops and evaluates federated learning algorithms for personalizing machine learning models across heterogeneous client data distributions. | 154 |
 jinheonbaek/fed-pub | Personalized Subgraph Federated Learning framework for distributed machine learning | 44 |
 gingsmith/fmtl | A framework for collaborative learning across multiple tasks and datasets in a distributed manner | 129 |
 xtra-computing/fedov | Develops a framework to address label skews in one-shot federated learning by partitioning data and adapting models. | 14 |