coteaching_plus 
 Co-teaching algorithm
 This project implements a PyTorch-based co-teaching algorithm to improve generalization against label corruption in machine learning.
ICML'19: How does Disagreement Help Generalization against Label Corruption?
21 stars
 1 watching
 3 forks
 
Language: Python 
last commit: over 6 years ago  Related projects:
| Repository | Description | Stars | 
|---|---|---|
|    |  Develops a robust training method for deep neural networks using noisy labels | 494 | 
|    |  An implementation of a deep learning algorithm for graph data | 270 | 
|    |  A comprehensive C programming project covering various algorithms and data structures | 749 | 
|    |  A PyTorch implementation of a clustering algorithm for graph neural networks | 788 | 
|    |  A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,044 | 
|    |  An implementation of Masking, a method to improve the robustness of deep neural networks under noisy supervision | 54 | 
|    |  A PyTorch implementation of node representation learning using multiple social contexts | 213 | 
|    |  A PyTorch implementation of a method for improving semi-supervised learning in federated settings by adapting pseudo labels to balance classes. | 7 | 
|    |  Develops a PyTorch implementation of an enhanced vision language model | 93 | 
|    |  A C++ implementation of PyTorch tutorials | 1,978 | 
|    |  An open-source software project providing tools and examples for building machine learning models in Java | 13 | 
|    |  A language that facilitates designing machine learning models with flexible configurations | 64 | 
|    |  A collection of examples and code snippets teaching machine learning concepts to security professionals through hands-on Python projects | 151 | 
|    |  An R package implementing a community detection algorithm using graph degree betweenness. | 37 | 
|    |  Implementation of graph convolutional network algorithms with sampling techniques to improve learning speed and efficiency | 520 |