ICML 2018oral84 citations
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints
Ehsan Kazemi, Morteza Zadimoghaddam, Amin Karbasi
Abstract
Can we efficiently extract useful information from a large user-generated dataset while protecting the privacy of the users and/or ensuring fairness in representation? We cast this problem as an instance of a deletion-robust submodular maximization where part of the data may be deleted or masked due to privacy concerns or fairness criteria. We propose the first memory-efficient centralized, streaming, and distributed methods with constant-factor approximation guarantees against
BibTeX
@InProceedings{pmlr-v80-kazemi18a,
title = {Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints},
author = {Kazemi, Ehsan and Zadimoghaddam, Morteza and Karbasi, Amin},
booktitle = {Proceedings of the 35th International Conference on Machine Learning},
pages = {2544--2553},
year = {2018},
editor = {Dy, Jennifer and Krause, Andreas},
volume = {80},
series = {Proceedings of Machine Learning Research},
month = {10--15 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v80/kazemi18a/kazemi18a.pdf},
url = {https://proceedings.mlr.press/v80/kazemi18a.html},
abstract = {Can we efficiently extract useful information from a large user-generated dataset while protecting the privacy of the users and/or ensuring fairness in representation? We cast this problem as an instance of a deletion-robust submodular maximization where part of the data may be deleted or masked due to privacy concerns or fairness criteria. We propose the first memory-efficient centralized, streaming, and distributed methods with constant-factor approximation guarantees against