# Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors

arXiv: https://arxiv.org/abs/2608.16700 · HTML: https://mlsanity.com/paper/2608.16700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 17 of 17)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers](https://mlsanity.com/paper/2301.11578/) (2023)
- [Learn to Forget: Machine Unlearning via Neuron Masking](https://mlsanity.com/paper/2003.10933/) (2020)
- [PUMA: Performance Unchanged Model Augmentation for Training Data Removal](https://mlsanity.com/paper/2203.00846/) (2022)
- [Knowledge Removal in Sampling-based Bayesian Inference](https://mlsanity.com/paper/2203.12964/) (2022)
- [Nearest-Neighbour-Induced Isolation Similarity and its Impact on Density-Based Clustering](https://mlsanity.com/paper/1907.00378/) (2019)

## Abstract (arXiv)

Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their legal right to have their data Df removed from a machine learning model. This process is typically accomplished via the use of an unlearning function denoted as U. Existing methods focus on designing an intricate U to unlearn Df subset D from a previous model A(D), so that the unlearned model performs as closely as possible to the retrained model A(D setminus Df). However, these methods often suffer from high computational costs when dealing with massive training data, as the complex structures of U become a bottleneck even for models with fewer parameters. Inspired by Learning to Optimize, we introduce the first learning-based model-agnostic approach, Learning-to-UnLearn (L2UL). Our core insight is to shift from manually designing U to learning the unlearning behaviors from a distribution perspective, thereby acquiring a simple and efficient U via learning. Our experimental results demonstrate that the accuracy achieved by L2UL is comparable to that of retraining while exhibiting impressive efficiency, particularly in data-intensive scenarios. Furthermore, we validate the performance and scalability of our method on larger models ResNet.