Welcome to the Machine Unlearning Workshop!
This repository brings together state-of-the-art projects and resources for exploring, understanding, and experimenting with machine unlearning techniques.
| Project Name | Description | Repository Link |
|---|---|---|
| Zero-Shot Unlearning | Efficiently unlearn data from models without retraining from scratch. | zero-shot-unlearning |
| Fast Machine Unlearning | Fast and scalable approaches for removing data influence from trained models. | Fast-Machine-Unlearning |
| Deep Regression Unlearning | Techniques for unlearning in deep regression models. | deep-regression-unlearning |
| Bad Teaching Unlearning | Methods for identifying and unlearning harmful or misleading data in training sets. | bad-teaching-unlearning |
-
Clone this repository:
git clone https://github.com/respailab/Machine-Unlearning-Workshop.git cd Machine-Unlearning-Workshop -
Explore each project:
- Each folder contains its own README and instructions.
- You can run experiments, review code, and try out unlearning methods.
Machine unlearning refers to techniques that enable a trained machine learning model to forget or remove the influence of specific data points, often for privacy, compliance, or fairness reasons.
This workshop provides hands-on resources to learn, experiment, and innovate in this emerging field.
Take a look to gain overall idea of unlearning - Machine unlearning demo
Machine-Unlearning-Workshop/
│
├── zero-shot-unlearning/
├── Fast-Machine-Unlearning/
├── deep-regression-unlearning/
└── bad-teaching-unlearning/
Contributions, questions, and suggestions are welcome!
Feel free to open issues or pull requests for improvements.
- respailab for maintaining the original repositories.
Happy Unlearning!