# Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices arXiv: https://arxiv.org/abs/2410.10128 ยท HTML: https://mlsanity.com/paper/2410.10128/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Machine unlearning, one of 12 directions in LLM safety and security. - Builds on 27 of its 61 references that are in the map. - First posted on arXiv 14 Oct 2024. ## Placed in - LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/) ## Builds on (most cited first, 27 of 27) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018) - [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019) - [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017) - [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018) - [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019) - [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024) - [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019) - [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020) - [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021) - [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020) - [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019) - [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019) - [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023) - [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021) - [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021) - [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021) - [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020) - [Machine Unlearning for Random Forests](https://mlsanity.com/paper/2009.05567/) (2020) - [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022) - [Vision Transformer Pruning](https://mlsanity.com/paper/2104.08500/) (2021) - [Manipulating SGD with Data Ordering Attacks](https://mlsanity.com/paper/2104.09667/) (2021) - [Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning](https://mlsanity.com/paper/2404.03233/) (2024) - [Membership Inference Attacks and Defenses in Neural Network Pruning](https://mlsanity.com/paper/2202.03335/) (2022) - [A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services](https://mlsanity.com/paper/2309.08230/) (2023) - [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023) ## Built on by (most cited first, 9 of 9) - [Exact Unlearning of Finetuning Data via Model Merging at Scale](https://mlsanity.com/paper/2504.04626/) (2025) - [Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM](https://mlsanity.com/paper/2505.24379/) (2025) - [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025) - [ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs](https://mlsanity.com/paper/2512.09953/) (2025) - [Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks](https://mlsanity.com/paper/2510.06629/) (2025) - [FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI](https://mlsanity.com/paper/2511.05605/) (2025) - [FedSGT: Exact Federated Unlearning via Sequential Group-based Training](https://mlsanity.com/paper/2511.23393/) (2025) - [FIT to Forget: Robust Continual Unlearning for Large Language Models](https://mlsanity.com/paper/2601.21682/) (2026) - [When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks](https://mlsanity.com/paper/2607.28829/) (2026) ## Abstract (arXiv) The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize information from the training data, increasing the potential privacy risk to users. To address this, multiple machine unlearning techniques have been developed and deployed. Among them, approximate unlearning is a popular solution, but recent studies report that its unlearning effectiveness is not fully guaranteed. Another approach, exact unlearning, tackles this issue by discarding the data and retraining the model from scratch, but at the cost of considerable computational and memory resources. However, not all devices have the capability to perform such retraining. In numerous machine learning applications, such as edge devices, Internet-of-Things (IoT), mobile devices, and satellites, resources are constrained, posing challenges for deploying existing exact unlearning methods. In this study, we propose a Constraint-aware Adaptive Exact Unlearning System at the network Edge (CAUSE), an approach to enabling exact unlearning on resource-constrained devices. Aiming to minimize the retrain overhead by storing sub-models on the resource-constrained device, CAUSE innovatively applies a Fibonacci-based replacement strategy and updates the number of shards adaptively in the user-based data partition process. To further improve the effectiveness of memory usage, CAUSE leverages the advantage of model pruning to save memory via compression with minimal accuracy sacrifice. The experimental results demonstrate that CAUSE significantly outperforms other representative systems in realizing exact unlearning on the resource-constrained device by 9.23%-80.86%, 66.21%-83.46%, and 5.26%-194.13% in terms of unlearning speed, energy consumption, and accuracy.