fedl2p
Personalized Learning Model Trainer
This project enables personalized learning models by collaborating on learning the best strategy for each client
[NeurIPS'23] FedL2P: Federated Learning to Personalize
19 stars
2 watching
3 forks
Language: Python
last commit: 9 months ago Related projects:
Repository | Description | Stars |
---|---|---|
| A Python implementation of Personalized Federated Learning with Graph using PyTorch. | 49 |
| A framework that separates feature information from data in federated learning to enable personalized models. | 25 |
| A framework for federated learning with partial model personalization | 2 |
| An implementation of federated learning with prototype-based methods across heterogeneous clients | 134 |
| A method for personalizing machine learning models in federated learning settings with adaptive differential privacy to improve performance and robustness | 57 |
| Enabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data | 56 |
| An implementation of personalized federated learning using variational Bayesian inference on the MNIST dataset | 52 |
| Investigates transfer learning in federated learning by guiding the last layer with pre-trained models | 7 |
| 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 |
| An implementation of cross-silo federated learning with adaptability to statistical heterogeneity | 12 |
| Improves machine learning models for personalized performance under evolving test distributions in distributed environments | 53 |
| Provides code for a federated learning algorithm to optimize machine learning models in a distributed setting. | 14 |
| An implementation of a federated learning algorithm for handling heterogeneous data | 6 |
| This project presents an approach to federated learning that leverages unsupervised techniques to adapt models to unlabeled data without requiring labels. | 33 |
| An approach to heterogeneous federated learning allowing for model training on diverse devices with varying resources. | 61 |