phuber
Gradient clipping mitigation
An implementation of gradient clipping as a method to mitigate the effects of noisy labels in machine learning models
[Re] Can gradient clipping mitigate label noise? (ML Reproducibility Challenge 2020)
14 stars
3 watching
6 forks
Language: Python
last commit: 6 months ago gradient-clippinglabel-noisepytorchrobust-learning
Related projects:
| Repository | Description | Stars |
|---|---|---|
 xiaoboxia/cdr | An implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks | 75 |
 pxiangwu/topofilter | Develops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning. | 30 |
 pkmr06/pytorch-smoothgrad | PyTorch implementation of a technique to improve the interpretability of deep learning models by adding noise to the gradients | 168 |
 mmazeika/glc | A method to train deep learning classifiers on noisy labels using a small set of trusted data | 86 |
 moucheng2017/med-noisy-labels | Provides PyTorch implementation of a method to address noisy labels in medical image segmentation. | 71 |
 xlearning-scu/2021-cvpr-mrl | Develops a robust learning framework to handle noisy labels in multimodal data and improve cross-modal retrieval. | 13 |
 lijunnan1992/dividemix | A PyTorch implementation of a semi-supervised learning framework for training deep neural networks with noisy labels by dynamically dividing the data into clean and noisy sets. | 546 |
 hongxin001/odnl | An implementation of a method to improve model robustness against inherent label noise in machine learning models | 19 |
| xiaoboxia/t-revision | A PyTorch implementation of a method for learning with noisy labels in deep neural networks | 97 |
 dr-darryl-wright/noisy-labels-with-bootstrapping | An implementation of training deep neural networks on noisy labels with bootstrapping using Keras | 22 |
 udibr/noisy_labels | This project explores how to adapt neural networks to noisy labels by introducing a mechanism that can learn to correct the errors. | 118 |
 gdisag/gradient_disaggregation | An algorithm that breaks secure aggregation protocols in federated learning by recovering individual model updates from aggregated sums | 14 |
 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 |
 neuralmagic/sparseml | Enables the creation of smaller neural network models through efficient pruning and quantization techniques | 2,083 |
 paulalbert31/labelnoisecorrection | An implementation of an unsupervised label noise modeling and loss correction approach for deep learning. | 221 |