SFAT
Heterogeneity fixer
Combating heterogeneity in federated learning by combining adversarial training with client-wise slack during aggregation
[ICLR 2023] "Combating Exacerbated Heterogeneity for Robust Models in Federated Learning"
28 stars
2 watching
7 forks
Language: Python
last commit: over 1 year ago adversarial-learningdata-heterogeneityfederated-adversarial-learningfederated-learningrobust-machine-learning
Related projects:
| Repository | Description | Stars |
|---|---|---|
 pengyang7881187/fedrl | Enabling multiple agents to learn from heterogeneous environments without sharing their knowledge or data | 54 |
 zackzikaixiao/fedgrab | A tool for training federated learning models with adaptive gradient balancing to handle class imbalance in multi-client scenarios. | 13 |
 mmendiet/fedalign | A federated learning framework designed to mitigate data heterogeneity in distributed learning settings. | 55 |
 aiot-mlsys-lab/fedrolex | An approach to heterogeneous federated learning allowing for model training on diverse devices with varying resources. | 61 |
 dawenzi098/sfl-structural-federated-learning | A Python implementation of Personalized Federated Learning with Graph using PyTorch. | 50 |
 lyn1874/fedpvr | An implementation of a federated learning algorithm for handling heterogeneous data | 6 |
 zhenqincn/fedapen | An implementation of cross-silo federated learning with adaptability to statistical heterogeneity | 10 |
 omarfoq/fedem | Develops and evaluates federated learning algorithms for personalizing machine learning models across heterogeneous client data distributions. | 154 |
 haozzh/fedcr | Evaluates various methods for federated learning on different models and tasks. | 17 |
 yamingguo98/fediir | An implementation of a federated learning algorithm that generalizes to out-of-distribution scenarios using implicit invariant relationships | 9 |
 yuetan031/fedproto | An implementation of federated learning with prototype-based methods across heterogeneous clients | 133 |
 xtra-computing/fedov | Develops a framework to address label skews in one-shot federated learning by partitioning data and adapting models. | 14 |
 xiyuanyang45/dynamicpfl | A method for personalizing machine learning models in federated learning settings with adaptive differential privacy to improve performance and robustness | 51 |
 diaoenmao/heterofl-computation-and-communication-efficient-federated-learning-for-heterogeneous-clients | An implementation of efficient federated learning algorithms for heterogeneous clients | 152 |
 alshedivat/fedpa | A modular JAX implementation of federated learning via posterior averaging for decentralized optimization | 49 |