Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics

• URL: http://arxiv.org/abs/2401.05146v3
• Date: Tue, 05 Nov 2024 13:47:50 GMT
• Title: Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
• Authors: Nicolò Romandini, Alessio Mora, Carlo Mazzocca, Rebecca Montanari, Paolo Bellavista,
• Abstract summary: Federated unlearning (FU) algorithms efficiently remove clients' contributions without full model retraining. This article provides background concepts, empirical evidence, and practical guidelines to design/implement efficient FU schemes.
• Score: 2.7456900944642686
• License:
• Abstract: Federated learning (FL) enables collaborative training of a machine learning (ML) model across multiple parties, facilitating the preservation of users' and institutions' privacy by maintaining data stored locally. Instead of centralizing raw data, FL exchanges locally refined model parameters to build a global model incrementally. While FL is more compliant with emerging regulations such as the European General Data Protection Regulation (GDPR), ensuring the right to be forgotten in this context - allowing FL participants to remove their data contributions from the learned model - remains unclear. In addition, it is recognized that malicious clients may inject backdoors into the global model through updates, e.g., to generate mispredictions on specially crafted data examples. Consequently, there is the need for mechanisms that can guarantee individuals the possibility to remove their data and erase malicious contributions even after aggregation, without compromising the already acquired "good" knowledge. This highlights the necessity for novel federated unlearning (FU) algorithms, which can efficiently remove specific clients' contributions without full model retraining. This article provides background concepts, empirical evidence, and practical guidelines to design/implement efficient FU schemes. This study includes a detailed analysis of the metrics for evaluating unlearning in FL and presents an in-depth literature review categorizing state-of-the-art FU contributions under a novel taxonomy. Finally, we outline the most relevant and still open technical challenges, by identifying the most promising research directions in the field.

Related papers

• FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher [4.291269657919828]
  Federated Learning (FL) promises better privacy guarantees for individuals' data when machine learning models are collaboratively trained. When an FL participant exercises its right to be forgotten, i.e., to detach from the FL framework it has participated, the FL solution should perform all the necessary steps. We propose FedQUIT, a novel algorithm that uses knowledge distillation to scrub the contribution of the forgetting data from an FL global model.
  arXiv  Detail & Related papers  (2024-08-14T14:36:28Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• SoK: Challenges and Opportunities in Federated Unlearning [32.0365189539138]
  This SoK paper aims to take a deep look at the emphfederated unlearning literature, with the goal of identifying research trends and challenges in this emerging field.
  arXiv  Detail & Related papers  (2024-03-04T19:35:08Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Tunable Soft Prompts are Messengers in Federated Learning [55.924749085481544]
  Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources. The lack of model privacy protection in FL becomes an unneglectable challenge. We propose a novel FL training approach that accomplishes information exchange among participants via tunable soft prompts.
  arXiv  Detail & Related papers  (2023-11-12T11:01:10Z)
• A Survey on Federated Unlearning: Challenges, Methods, and Future Directions [21.90319100485268]
  In recent years, the notion of the right to be forgotten" (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety. Machine unlearning (MU) has gained considerable attention which allows an ML model to selectively eliminate identifiable information. FU has emerged to confront the challenge of data erasure within federated learning settings.
  arXiv  Detail & Related papers  (2023-10-31T13:32:00Z)
• A Survey of Federated Unlearning: A Taxonomy, Challenges and Future Directions [71.16718184611673]
  The evolution of privacy-preserving Federated Learning (FL) has led to an increasing demand for implementing the right to be forgotten. The implementation of selective forgetting is particularly challenging in FL due to its decentralized nature. Federated Unlearning (FU) emerges as a strategic solution to address the increasing need for data privacy.
  arXiv  Detail & Related papers  (2023-10-30T01:34:33Z)
• Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning [19.505644178449046]
  We propose a novel and general method named Federated Self-supervised Learning with Feature-correlation based Aggregation (FedFoA) Our insight is to utilize feature correlation to align the feature mappings and calibrate the local model updates across clients during their local training process. We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.
  arXiv  Detail & Related papers  (2022-11-14T13:59:50Z)
• Knowledge Distillation for Federated Learning: a Practical Guide [8.2791533759453]
  Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however, have well known limits. We provide a review of KD-based algorithms tailored for specific FL issues.
  arXiv  Detail & Related papers  (2022-11-09T08:31:23Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• Do Gradient Inversion Attacks Make Federated Learning Unsafe? [70.0231254112197]
  Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. Recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in real FL use-cases and provide a new baseline attack.
  arXiv  Detail & Related papers  (2022-02-14T18:33:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.