# Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition

arXiv: https://arxiv.org/abs/2605.04713 · HTML: https://mlsanity.com/paper/2605.04713/

## 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 28 of its 35 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [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)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Identifying Mislabeled Data using the Area Under the Margin Ranking](https://mlsanity.com/paper/2001.10528/) (2020)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [DAiSEE: Towards User Engagement Recognition in the Wild](https://mlsanity.com/paper/1609.01885/) (2016)
- [Machine Unlearning: A Comprehensive Survey](https://mlsanity.com/paper/2405.07406/) (2024)
- [Generative Unlearning for Any Identity](https://mlsanity.com/paper/2405.09879/) (2024)
- [Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselines](https://mlsanity.com/paper/2302.00431/) (2023)
- [TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals](https://mlsanity.com/paper/2404.09474/) (2024)
- [Analyzing Participants' Engagement during Online Meetings Using Unsupervised Remote Photoplethysmography with Behavioral Features](https://mlsanity.com/paper/2404.04394/) (2024)
- [Computational Analysis of Stress, Depression and Engagement in Mental Health: A Survey](https://mlsanity.com/paper/2403.08824/) (2024)
- [CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels](https://mlsanity.com/paper/2312.09066/) (2023)
- [Vision Large Language Models Are Good Noise Handlers in Engagement Analysis](https://mlsanity.com/paper/2511.14749/) (2025)
- [PriorNet: Prior-Guided Engagement Estimation from Face Video](https://mlsanity.com/paper/2605.03615/) (2026)

## Abstract (arXiv)

Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision, making post-hoc dataset revision a practical problem. Existing noisy-label and data-cleaning methods largely operate at the sample level before or during training, but do not directly address a different question: once a model has already been trained, can the influence of an entire problematic subject be removed without full retraining? We study this setting through subject-level machine unlearning as a post-hoc sanitization mechanism for engagement recognition. Starting from a baseline trained on all subjects, we rank candidate harmful subjects using a model-dependent proxy, apply a lightweight approximate unlearning update, and compare the result against an oracle model retrained from scratch on the retained subjects only. We instantiate this protocol on DAiSEE and EngageNet using Tensor-Convolution and Convolution-Transformer Network (TCCT-Net) as a fixed platform and evaluate three matched model states under the same removal scenario: baseline, unlearned, and oracle. In representative K=3 forget-set settings, the unlearned model recovers 89.3% and 92.5% of the oracle gain on EngageNet and DAiSEE, respectively, at roughly one quarter of retraining cost. Across the tested small-audit regimes, effectiveness is strongest at an intermediate forget-set size, indicating that approximate subject-level unlearning is a useful low-cost correction mechanism, but one whose benefit depends on subject selection quality and removal regime.