# eCIL-MU: Embedding based Class Incremental Learning and Machine Unlearning

arXiv: https://arxiv.org/abs/2401.02457 · HTML: https://mlsanity.com/paper/2401.02457/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Placed in

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

## Builds on (most cited first, 9 of 9)

- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (2022)
- [VeriFi: Towards Verifiable Federated Unlearning](https://mlsanity.com/paper/2205.12709/) (2022)
- [Manu: A Cloud Native Vector Database Management System](https://mlsanity.com/paper/2206.13843/) (2022)
- [PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models](https://mlsanity.com/paper/2002.11791/) (2020)

## Built on by (most cited first, 4 of 4)

- [Machine unlearning through fine-grained model parameters perturbation](https://mlsanity.com/paper/2401.04385/) (2024)
- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)
- [Parallel Unlearning in Inherited Model Networks](https://mlsanity.com/paper/2408.08493/) (2024)
- [Privacy-Aware Lifelong Learning](https://mlsanity.com/paper/2505.10941/) (2025)

## Abstract (arXiv)

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about previously learned ones in such dynamic environments. It might also be necessary to also eliminate the influence of related categories on the model to adapt to reclassification. We thus introduce class-level machine unlearning (MU) within CIL. Typically, MU methods tend to be time-consuming and can potentially harm the model's performance. A continuous stream of unlearning requests could lead to catastrophic forgetting. To address these issues, we propose a non-destructive eCIL-MU framework based on embedding techniques to map data into vectors and then be stored in vector databases. Our approach exploits the overlap between CIL and MU tasks for acceleration. Experiments demonstrate the capability of achieving unlearning effectiveness and orders of magnitude (upto ~ 278×) of acceleration.