Fair and green hyperparameter optimization via multi-objective and multiple information source Bayesian optimization

Author:

Candelieri AntonioORCID,Ponti AndreaORCID,Archetti FrancescoORCID

Abstract

AbstractIt has been recently remarked that focusing only on accuracy in searching for optimal Machine Learning models amplifies biases contained in the data, leading to unfair predictions and decision supports. Recently, multi-objective hyperparameter optimization has been proposed to search for Machine Learning models which offer equally Pareto-efficient trade-offs between accuracy and fairness. Although these approaches proved to be more versatile than fairness-aware Machine Learning algorithms—which instead optimize accuracy constrained to some threshold on fairness—their carbon footprint could be dramatic, due to the large amount of energy required in the case of large datasets. We propose an approach named FanG-HPO: fair and green hyperparameter optimization (HPO), based on both multi-objective and multiple information source Bayesian optimization. FanG-HPO uses subsets of the large dataset to obtain cheap approximations (aka information sources) of both accuracy and fairness, and multi-objective Bayesian optimization to efficiently identify Pareto-efficient (accurate and fair) Machine Learning models. Experiments consider four benchmark (fairness) datasets and four Machine Learning algorithms, and provide an assessment of FanG-HPO against both fairness-aware Machine Learning approaches and two state-of-the-art Bayesian optimization tools addressing multi-objective and energy-aware optimization.

Funder

Università degli Studi di Milano - Bicocca

Publisher

Springer Science and Business Media LLC

Reference62 articles.

1. Archetti, F., & Candelieri, A. (2019). Bayesian optimization and data science. Springer.

2. Ariafar, S., Mariet, Z., Brooks, D.H., Dy, J.G. & Snoek, J. (2021). Faster & more reliable tuning of neural networks: Bayesian optimization with importance sampling. In AISTATS (pp. 3961–3969).

3. Barocas, S., Hardt, M. & Narayanan, A. (2017). Fairness in machine learning. NIPS tutorial.

4. Belakaria, S. & Deshwal, A. (2019). Max-value entropy search for multi-objective Bayesian optimization. In International conference on neural information processing systems (NeurIPS).

5. Belakaria, S., Deshwal, A., & Doppa, J. R. (2020). Multi-fidelity multi-objective Bayesian optimization: an output space entropy search approach. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 10035–10043.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3