CAREER: Information-Theoretic Foundations of Fairness in Machine Learning

职业：机器学习公平性的信息理论基础

基本信息

批准号：
1845852
负责人：
Flavio Calmon
金额：
$ 54.79万
依托单位：
Harvard University
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-02-01 至 2024-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1845852&HistoricalAwards=false
关键词：
CAREER Information Theoretic Foundations Fairness

项目摘要

Machine learning algorithms can identify complex patterns in very large datasets. These algorithms are increasingly used in applications of significant social consequence, such as loan approval, hiring, and bail and sentencing decisions. However, real-world data may reflect discrimination patterns that exist in society at large. Consequently, decisions based on algorithms that learn from data are at risk of inheriting and, ultimately, reinforcing discriminatory and unfair social biases. This project aims to precisely characterize the operational limits of discrimination discovery and control in machine learning by combining legal and social science definitions of fairness with powerful mathematical tools from information theory, statistics, and optimization. This cross-disciplinary effort aims to provide fundamental theory and design guidelines for data scientists and engineers who will create the next generation of fair data-driven algorithms and applications. The technical results of this project will also inform the debate surrounding the social impact of machine learning. Moreover, this research will be used as a vessel for engaging students and researchers from diverse backgrounds in the applicability of information theory, machine learning, optimization, and, more broadly, math and engineering to social challenges.Automated methods for discovering and controlling discrimination in machine learning inherently face a trade-off between fairness and accuracy, and are limited by the dimensionality of the underlying data. This project creates a comprehensive information-theoretic framework that captures the limits of discrimination control by determining (i) how to systematically identify data features that may lead to discrimination; (ii) how to ensure fairness by producing new, information-theoretically grounded data representations; (iii) the fundamental information-theoretic trade-offs between fairness, distortion, and accuracy; and (iv) the impact of finite samples in discrimination detection and mitigation. The key advantage of the information-theoretic methodology adopted in this project is that it captures fundamental, algorithm-independent properties of discrimination, while being fertile ground for the development of novel mathematical tools and models relevant to both data scientists and information theorists. The theoretical component of this research weaves new connections between information theory and robust statistics by analyzing the impact of local perturbations of probability distributions on discrimination metrics, and creates new information-theoretic models useful in discrimination control, privacy, and representation learning. The applied component of this research develops robust, data-driven methods for measuring and mitigating discrimination that are immediately relevant for fair algorithmic decision-making in applications of consequence.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

机器学习算法可以识别非常大的数据集中的复杂模式。这些算法越来越多地用于具有重大社会影响的应用，例如贷款审批、招聘、保释和量刑决策。然而，现实世界的数据可能反映了整个社会存在的歧视模式。因此，基于从数据中学习的算法做出的决策存在继承并最终强化歧视性和不公平社会偏见的风险。该项目旨在通过将公平的法律和社会科学定义与来自信息论、统计学和优化的强大数学工具相结合，精确描述机器学习中歧视发现和控制的操作限制。这项跨学科的工作旨在为数据科学家和工程师提供基础理论和设计指南，帮助他们创建下一代公平的数据驱动算法和应用程序。该项目的技术成果还将为围绕机器学习的社会影响的辩论提供信息。此外，这项研究将成为吸引来自不同背景的学生和研究人员参与信息论、机器学习、优化以及更广泛的数学和工程学应对社会挑战的工具。发现和控制歧视的自动化方法机器学习本质上面临着公平性和准确性之间的权衡，并且受到底层数据维度的限制。该项目创建了一个全面的信息理论框架，通过确定（i）如何系统地识别可能导致歧视的数据特征来捕捉歧视控制的局限性； (ii) 如何通过产生新的、基于信息理论的数据表示来确保公平性； (iii) 公平性、扭曲性和准确性之间的基本信息论权衡； (iv) 有限样本对歧视检测和缓解的影响。该项目采用的信息论方法的主要优势在于，它捕获了基本的、独立于算法的歧视属性，同时为开发与数据科学家和信息理论家相关的新颖数学工具和模型提供了肥沃的土壤。这项研究的理论部分通过分析概率分布的局部扰动对歧视度量的影响，在信息论和稳健统计之间建立了新的联系，并创建了可用于歧视控制、隐私和表征学习的新信息理论模型。这项研究的应用部分开发了强大的、数据驱动的方法来衡量和减轻歧视，这些方法与结果应用中的公平算法决策直接相关。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准。

项目成果

期刊论文数量（33）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Bottleneck Problems: An Information and Estimation-Theoretic View

瓶颈问题：信息和估计理论的观点

DOI：
10.3390/e22111325
发表时间：
2020-11
期刊：
Entropy
影响因子：
2.7
作者：
Asoodeh, Shahab;Calmon, Flavio P.
通讯作者：
Calmon, Flavio P.

Local Differential Privacy Is Equivalent to Contraction of an $f$-Divergence

局部差分隐私相当于 $f$-Divergence 的收缩

DOI：
10.1109/isit45174.2021.9517999
发表时间：
2021-07
期刊：
2021 IEEE International Symposium on Information Theory (ISIT
影响因子：
0
作者：
Asoodeh, Shahab;Aliakbarpour, Maryam;Calmon, Flavio P.
通讯作者：
Calmon, Flavio P.

Privacy Amplification of Iterative Algorithms via Contraction Coefficients

通过收缩系数实现迭代算法的隐私放大

DOI：
10.1109/isit44484.2020.9174133
发表时间：
2020-06
期刊：
Proc. of the 2020 IEEE International Symposium on Information Theory (ISIT
影响因子：
0
作者：
Asoodeh, Shahab;Diaz, Mario;Calmon, Flavio P.
通讯作者：
Calmon, Flavio P.

A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences

更好的绑定提供一百轮：通过 f-Divergences 增强隐私保证

DOI：
10.1109/isit44484.2020.9174015
发表时间：
2020-06
期刊：
Proc. of the 2020 IEEE International Symposium on Information Theory (ISIT
影响因子：
0
作者：
Asoodeh, Shahab;Liao, Jiachun;Calmon, Flavio P.;Kosut, Oliver;Sankar, Lalitha
通讯作者：
Sankar, Lalitha

Arbitrary Decisions are a Hidden Cost of Differentially Private Training

武断的决定是差别化私人训练的隐性成本

DOI：
10.1145/3593013.3594103
发表时间：
2023-02-28
期刊：
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency
影响因子：
0
作者：
B. Kulynych;Hsiang Hsu;C. Troncoso;F. Calmon
通讯作者：
F. Calmon