fed_het
Architecture design for FL
This project investigates how to design architectures that enable better performance in federated learning systems, particularly for visual recognition tasks.
10 stars
1 watching
1 forks
Language: Python
last commit: almost 3 years agoRelated projects:
| Repository | Description | Stars |
|---|---|---|
 federatedai/fedvision | A federated learning platform for computer vision tasks using PaddleFL and PaddleDetection | 112 |
 harliwu/fedamd | This project presents an approach to federated learning with partial client participation by optimizing anchor selection for improving model accuracy and convergence. | 2 |
 zoesgithub/fedreg | An algorithm to improve convergence rates and protect privacy in Federated Learning by addressing the catastrophic forgetting issue during local training | 26 |
 yuetan031/fedproto | An implementation of federated learning with prototype-based methods across heterogeneous clients | 134 |
| federatedai/fate-client | Provides tools and APIs for designing, scheduling, and running federated machine learning jobs in a secure and efficient manner. | 3 |
 ibm/fl-arbitrary-participation | Analyzes Federated Learning with Arbitrary Client Participation using various optimization strategies and datasets. | 4 |
 mmorafah/pacfl | Implementation of federated learning algorithms for distributed machine learning on private client data | 37 |
 substra/substra | Enables the training and validation of machine learning models on distributed datasets in a secure and scalable manner. | 274 |
 lyn1874/fedpvr | An implementation of a federated learning algorithm for handling heterogeneous data | 6 |
 haozzh/fedcr | Evaluates various methods for federated learning on different models and tasks. | 19 |
 mediabrain-sjtu/fedgela | This project enables federated learning across partially class-disjoint data with curated bilateral curation. | 11 |
 sarababakn/mfcl-neurips23 | An approach to mitigating catastrophic forgetting in federated class incremental learning for vision tasks using a generative model and data-free methods | 15 |
 alshedivat/fedpa | A modular JAX implementation of federated learning via posterior averaging for decentralized optimization | 50 |
| ibm/reprogrammble-fl | Improves utility-privacy tradeoff in federated learning by reprogramming models to balance data utility and user privacy. | 5 |
 pengyang7881187/fedrl | Enabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data | 56 |