icml2019_zeno
Fault-tolerant training method
An implementation of distributed stochastic gradient descent with fault-tolerance using suspicion-based methods.
14 stars
2 watching
5 forks
Language: Python
last commit: over 5 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 denissimon/distributed-model-training | An approach and implementation for distributed training of machine learning models on iOS devices using a central server. | 8 |
 cchio/deep-pwning | A tool to test the vulnerability of machine learning models to adversarial attacks | 559 |
 optimization-ai/icml2023_fedxl | An implementation of a federated learning algorithm for optimization problems with compositional pairwise risk optimization. | 2 |
 zackzikaixiao/fedgrab | A tool for training federated learning models with adaptive gradient balancing to handle class imbalance in multi-client scenarios. | 13 |
 zfancy/sfat | Combating heterogeneity in federated learning by combining adversarial training with client-wise slack during aggregation | 28 |
 xternalz/sdpoint | A deep learning method for optimizing convolutional neural networks by reducing computational cost while improving regularization and inference efficiency. | 18 |
 eth-sri/diffai | Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. | 218 |
 xmed-lab/rscfed | This project presents a federated semi-supervised learning approach to improve model performance on multiple datasets by leveraging random sampling consensus. | 46 |
 google-deepmind/meltingpot | Assesses generalization of multi-agent reinforcement learning algorithms to novel social situations | 620 |
 kimhc6028/forward-thinking-pytorch | An implementation of a novel neural network training method that builds and trains networks one layer at a time. | 65 |
 zhenqincn/fedapen | An implementation of cross-silo federated learning with adaptability to statistical heterogeneity | 10 |
 zoesgithub/fedreg | An algorithm to improve convergence rates and protect privacy in Federated Learning by addressing the catastrophic forgetting issue during local training | 26 |
 ml-postech/gradient-inversion-generative-image-prior | An implementation of a method to invert gradients in federated learning to potentially reveal sensitive client data | 39 |
 xiyuanyang45/dynamicpfl | A method for personalizing machine learning models in federated learning settings with adaptive differential privacy to improve performance and robustness | 51 |
 wyy-123-xyy/ra-fed | A Python implementation of a distributed machine learning framework for training neural networks on multiple GPUs | 6 |