# Machine Unlearning in Learned Databases: An Experimental Analysis

arXiv: https://arxiv.org/abs/2311.17276 · HTML: https://mlsanity.com/paper/2311.17276/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2023.

## Built on by (most cited first, 18 of 18)

- [To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models](https://mlsanity.com/paper/2405.03097/) (2024)
- [Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening](https://mlsanity.com/paper/2402.10098/) (2024)
- [Agents Are All You Need for LLM Unlearning](https://mlsanity.com/paper/2502.00406/) (2025)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification](https://mlsanity.com/paper/2412.16780/) (2024)
- [A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning](https://mlsanity.com/paper/2505.15178/) (2025)
- [How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective](https://mlsanity.com/paper/2406.16810/) (2024)
- [A Survey of Learned Indexes for the Multi-dimensional Space](https://mlsanity.com/paper/2403.06456/) (2024)
- [Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning](https://mlsanity.com/paper/2505.10859/) (2025)
- [In-Context Adaptation to Concept Drift for Learned Database Operations](https://mlsanity.com/paper/2505.04404/) (2025)
- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)
- [Detecting Instruction Fine-tuning Attacks using Influence Function](https://mlsanity.com/paper/2504.09026/) (2025)
- [CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution](https://mlsanity.com/paper/2412.05864/) (2024)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)
- [TraceHiding: Scalable Machine Unlearning for Mobility Data](https://mlsanity.com/paper/2509.17241/) (2025)
- [Forgetting by Pruning: Data Deletion in Join Cardinality Estimation](https://mlsanity.com/paper/2511.20293/) (2025)
- [FedSGT: Exact Federated Unlearning via Sequential Group-based Training](https://mlsanity.com/paper/2511.23393/) (2025)
- [Relationship-Aware Safety Unlearning for Multimodal LLMs](https://mlsanity.com/paper/2603.14185/) (2026)

## Abstract (arXiv)

Machine learning models based on neural networks (NNs) are enjoying ever-increasing attention in the DB community. However, an important issue has been largely overlooked, namely the challenge of dealing with the highly dynamic nature of DBs, where data updates are fundamental, highly-frequent operations. Although some recent research has addressed the issues of maintaining updated NN models in the presence of new data insertions, the effects of data deletions (a.k.a., "machine unlearning") remain a blind spot. With this work, for the first time to our knowledge, we pose and answer the following key questions: What is the effect of unlearning algorithms on NN-based DB models? How do these effects translate to effects on downstream DB tasks, such as selectivity estimation (SE), approximate query processing (AQP), data generation (DG), and upstream tasks like data classification (DC)? What metrics should we use to assess the impact and efficacy of unlearning algorithms in learned DBs? Is the problem of machine unlearning in DBs different from that of machine learning in DBs in the face of data insertions? Is the problem of machine unlearning for DBs different from unlearning in the ML literature? what are the overhead and efficiency of unlearning algorithms? What is the sensitivity of unlearning on batching delete operations? If we have a suitable unlearning algorithm, can we combine it with an algorithm handling data insertions en route to solving the general adaptability/updatability requirement in learned DBs in the face of both data inserts and deletes? We answer these questions using a comprehensive set of experiments, various unlearning algorithms, a variety of downstream DB tasks, and an upstream task (DC), each with different NNs, and using a variety of metrics on a variety of real datasets, making this also a first key step towards a benchmark for learned DB unlearning.