mlsanityData to 14 Oct 2026

Federated Unlearning for Human Activity Recognition

arXiv 2404.03659 ↗First posted 17 Jan 2024cs.LG cs.CRcited by 1

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

The rapid evolution of Internet of Things (IoT) technology has spurred the widespread adoption of Human Activity Recognition (HAR) in various daily life domains. Federated Learning (FL) is frequently utilized to build a global HAR model by aggregating user contributions without transmitting raw individual data. Despite substantial progress in user privacy protection with FL, challenges persist. Regulations like the General Data Protection Regulation (GDPR) empower users to request data removal, raising a new query in FL: How can a HAR client request data removal without compromising other clients' privacy? In response, we propose a lightweight machine unlearning method for refining the FL HAR model by selectively removing a portion of a client's training data. Our method employs a third-party dataset unrelated to model training. Using KL divergence as a loss function for fine-tuning, we aim to align the predicted probability distribution on forgotten data with the third-party dataset. Additionally, we introduce a membership inference evaluation method to assess unlearning effectiveness. Experimental results across diverse datasets show our method achieves unlearning accuracy comparable to textitretraining methods, resulting in speedups ranging from hundreds to thousands.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 9 of its 34 references that are in the map. First posted on arXiv 17 Jan 2024.

Builds on

9 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
  2. 2022Federated Unlearning with Knowledge Distillation24 Jan

Other references · 7

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  5. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  6. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  7. 2021Meta-HAR: Federated Representation Learning for Human Activity Recognitioncited by 21

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Private Data Leakage in Federated Human Activity Recognition for Wearable Healthcare Devices ↗
  2. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
  3. 2023Exploring Federated Unlearning: Review, Comparison, and Insights
  4. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions
  5. 2024Streamlined Federated Unlearning: Unite as One to Be Highly Efficient
  6. 2024Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
  7. 2025Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning
  8. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining