Machine Unlearning of Federated ClustersDownload PDF

Published: 01 Feb 2023, 19:21, Last Modified: 01 Feb 2023, 19:21ICLR 2023 posterReaders: Everyone
Keywords: federated learning, federated clustering, machine unlearning, secure aggregation
TL;DR: We propose the first known unlearning mechanism for federated clustering with privacy criteria that support simple, provable, and efficient data removal at the client and server level.
Abstract: Federated clustering is an unsupervised learning problem that arises in a number of practical applications, including personalized recommender and healthcare systems. With the adoption of recent laws ensuring the "right to be forgotten", the problem of machine unlearning for federated clustering methods has become of significant importance. This work proposes the first known unlearning mechanism for federated clustering with privacy criteria that support simple, provable, and efficient data removal at the client and server level. The gist of our approach is to combine special initialization procedures with quantization methods that allow for secure aggregation of estimated local cluster counts at the server unit. As part of our platform, we introduce secure compressed multiset aggregation (SCMA), which is of independent interest for secure sparse model aggregation. In order to simultaneously facilitate low communication complexity and secret sharing protocols, we integrate Reed-Solomon encoding with special evaluation points into the new SCMA pipeline and derive bounds on the time and communication complexity of different components of the scheme. Compared to completely retraining K-means++ locally and globally for each removal request, we obtain an average speed-up of roughly 84x across seven datasets, two of which contain biological and medical information that is subject to frequent unlearning requests.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)
24 Replies

Loading