Get the latest tech news
Machine Unlearning in 2024
Unlearning in 2024 Written by Ken Liu ∙ May 2024 As our ML models today become larger and their (pre-)training sets grow to inscrutable sizes, people are increasingly interested in the concept of machine unlearning to edit away undesired things like private data, stale knowledge, copyrighted materials, toxic/unsafe content, dangerous capabilities, and misinformation, without retraining models from scratch. Machine unlearning can be broadly described as removing the influences of training data from a trained model.
Or should they focus on the transformativeness axis of fair use and invest in deploying empirical guardrails, such as prompting, content moderation, and custom alignment to prevent the model from regurgitating training data? For safety-oriented applications, it is worth noting that unlearning should be treated as a post-training risk mitigation and defense mechanism, alongside existing tools like alignment fine-tuning and content filters. Acknowledgements: The author would like to thank Aryaman Arora, Jiaao Chen, Irena Gao, John Hewitt, Shengyuan Hu, Peter Kairouz, Sanmi Koyejo, Xiang Lisa Li, Percy Liang, Eric Mitchell, Rylan Schaeffer, Yijia Shao, Chenglei Si, Pratiksha Thaker, Xindi Wu for helpful discussions and feedback before and during the drafting of this post.
Or read this on Hacker News