# Cross-Domain Generalization in Machine Unlearning via Label-Conditioned Energy Magnitude Regularization

arXiv: https://arxiv.org/abs/2608.17942 · HTML: https://mlsanity.com/paper/2608.17942/

## 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 27 of its 36 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [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)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [A Theory of Generative ConvNet](https://mlsanity.com/paper/1602.03264/) (2016)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [Learning Energy-Based Models by Diffusion Recovery Likelihood](https://mlsanity.com/paper/2012.08125/) (2020)
- [On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models](https://mlsanity.com/paper/1903.12370/) (2019)
- [Can multi-label classification networks know what they don't know?](https://mlsanity.com/paper/2109.14162/) (2021)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Structured Prediction Energy Networks](https://mlsanity.com/paper/1511.06350/) (2015)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Energy-Based Models for Continual Learning](https://mlsanity.com/paper/2011.12216/) (2020)
- [Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems](https://mlsanity.com/paper/2311.02240/) (2023)
- [Machine Unlearning under Retain-Forget Entanglement](https://mlsanity.com/paper/2603.26569/) (2026)
- [Approximate Domain Unlearning for Vision-Language Models](https://mlsanity.com/paper/2510.08132/) (2025)
- [Benchmarking Approximate Inference Methods for Neural Structured Prediction](https://mlsanity.com/paper/1904.01138/) (2019)
- [Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach](https://mlsanity.com/paper/2512.14113/) (2025)

## Abstract (arXiv)

Machine unlearning removes the influence of specific data from a trained model. However, most methods treat the forgotten concept as isolated. In this paper, we study what happens to the rest of the model when a class is forgotten, using a label-conditioned energy-based model (EBM) that assigns per-class energies, making the effect directly observable. We forget a class by raising the energy of its image-label pairs, training with a forget term, a retain anchor to the pretrained model, a global margin, and an energy regularizer that stops the energy magnitudes from growing without limit. A propagation term applies the same forget signal to retain samples, weighted by each sample's DINOv2 similarity to the forget class, so forgetting reaches images that resemble it and leaves the rest untouched. We evaluate on two benchmark datasets: 1) On a subset of DomainNet across four visual domains, we forget tiger, lion, and scissors one at a time. Forgetting a class in the sketch domain also erases it from real, clipart, and painting, with forgetting error reaching 98% and 99% for lion and scissors, and the effect carrying over to the most similar class. 2) On CIFAR-10, we turn off the propagation term and forget each of the ten classes on its own. Forgetting is complete (100%), while the other nine classes retain 98.5% of their pre-unlearning accuracy on average.