knn-per
Personalized FL framework
A federated learning framework with personalized memorization using deep neural networks and k-nearest neighbors for collaborative learning of statistical models
Official code for "Personalized Federated Learning through Local Memorization" (ICML'22)
43 stars
2 watching
15 forks
Language: Python
last commit: over 1 year ago deep-learningfederated-learningmachine-learningpersonalized-federated-learningpytorch
Related projects:
Repository | Description | Stars |
---|---|---|
| Develops and evaluates federated learning algorithms for personalizing machine learning models across heterogeneous client data distributions. | 157 |
| A framework for federated learning with partial model personalization | 2 |
| Personalized Subgraph Federated Learning framework for distributed machine learning | 45 |
| Enables the training and validation of machine learning models on distributed datasets in a secure and scalable manner. | 274 |
| This project enables personalized federated learning with inferred collaboration graphs to improve the performance of machine learning models on non-IID (non-independent and identically distributed) datasets. | 26 |
| A framework for personalized federated learning to balance fairness and robustness in decentralized machine learning systems. | 138 |
| A framework for tackling heterogeneity and catastrophic forgetting in federated learning by leveraging cross-correlation and similarity learning | 97 |
| A toolkit for optimizing federated learning in cross-silo settings by designing efficient communication topologies | 30 |
| A framework for federated learning that leverages the neural tangent kernel to address statistical heterogeneity in distributed machine learning. | 3 |
| A framework for non-IID federated learning via neural propagation | 6 |
| A Python implementation of Personalized Federated Learning with Graph using PyTorch. | 49 |
| A unified framework for improving privacy and reducing communication overhead in distributed machine learning models. | 12 |
| An implementation of a personalized federated learning framework with decentralized sparse training and peer-to-peer communication protocol. | 72 |
| Develops a framework to balance competing goals in federated learning by decoupling generic and personalized prediction tasks. | 14 |
| A framework for personalized federated learning that creates dynamic models for each input instance and improves generalizability of global models. | 9 |