soteriafl
Federated Learning Experiments
Numerical experiments for private federated learning with communication compression algorithms
Code for paper SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression
7 stars
2 watching
1 forks
Language: Jupyter Notebook
last commit: over 2 years ago Related projects:
Repository | Description | Stars |
---|---|---|
| Personalized Subgraph Federated Learning framework for distributed machine learning | 45 |
| Provides code for Coresets in Vertical Federated Learning | 9 |
| An implementation of a defense against model inversion attacks in federated learning | 55 |
| An implementation of federated learning with prototype-based methods across heterogeneous clients | 134 |
| An implementation of efficient federated learning algorithms for heterogeneous clients | 155 |
| Evaluates various methods for federated learning on different models and tasks. | 19 |
| A method for personalizing machine learning models in federated learning settings with adaptive differential privacy to improve performance and robustness | 57 |
| An experiment comparing different federated learning approaches for image classification tasks with non-iid datasets. | 8 |
| A framework for attacking federated learning systems with adaptive backdoor attacks | 23 |
| A Python framework for collaborative machine learning without sharing sensitive data | 738 |
| This repository provides an implementation of a cross-silo federated learning framework with differential privacy mechanisms. | 25 |
| Enabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data | 56 |
| A framework for Federated Learning with Differential Privacy using PyTorch | 13 |
| 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 |
| This project enables federated learning across partially class-disjoint data with curated bilateral curation. | 11 |