A Survey on Federated Unlearning: Challenges and Opportunities

2024-03-04

AI Summary

This paper addresses machine unlearning in federated learning (FL) systems—specifically, how to compliantly remove the influence of specific user data on the global model under constraints of distribution, heterogeneity, interactivity, and data non-controllability. Method: Adopting a Systematization of Knowledge (SoK) approach, it establishes the first systematic taxonomy for federated unlearning, identifies fundamental reasons for the failure of centralized unlearning methods in FL, and clarifies essential distinctions in threat models, evaluation metrics, and experimental design. Contribution/Results: It distills three core challenges—poor reproducibility, lack of fairness, and weak robustness to heterogeneity—and proposes three future research directions: reproducible experimental paradigms, fair unlearning mechanisms, and heterogeneous-robust unlearning algorithms. The work provides theoretical foundations and methodological guidance for privacy-compliant FL governance under GDPR and CPRA.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Safety and Robustness
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Federated learning (FL), introduced in 2017, facilitates collaborative learning between non-trusting parties with no need for the parties to explicitly share their data among themselves. This allows training models on user data while respecting privacy regulations such as GDPR and CPRA. However, emerging privacy requirements may mandate model owners to be able to emph{forget} some learned data, e.g., when requested by data owners or law enforcement. This has given birth to an active field of research called emph{machine unlearning}. In the context of FL, many techniques developed for unlearning in centralized settings are not trivially applicable! This is due to the unique differences between centralized and distributed learning, in particular, interactivity, stochasticity, heterogeneity, and limited accessibility in FL. In response, a recent line of work has focused on developing unlearning mechanisms tailored to FL. This SoK paper aims to take a deep look at the emph{federated unlearning} literature, with the goal of identifying research trends and challenges in this emerging field. By carefully categorizing papers published on FL unlearning (since 2020), we aim to pinpoint the unique complexities of federated unlearning, highlighting limitations on directly applying centralized unlearning methods. We compare existing federated unlearning methods regarding influence removal and performance recovery, compare their threat models and assumptions, and discuss their implications and limitations. For instance, we analyze the experimental setup of FL unlearning studies from various perspectives, including data heterogeneity and its simulation, the datasets used for demonstration, and evaluation metrics. Our work aims to offer insights and suggestions for future research on federated unlearning.

Problem

• Addressing privacy requirements for forgetting learned data in federated learning
• Developing unlearning mechanisms tailored to federated learning's unique challenges
• Analyzing and comparing existing federated unlearning methods and their limitations

Innovation

• Federated learning enables privacy-compliant collaborative model training
• Machine unlearning addresses GDPR data removal requirements
• Specialized FL unlearning methods overcome centralized approach limitations