CAREER: Information-Theoretic Measures for Fairness and Explainability in High-Stakes Applications

职业:高风险应用中公平性和可解释性的信息论测量

基本信息

  • 批准号:
    2340006
  • 负责人:
  • 金额:
    $ 66.56万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2024
  • 资助国家:
    美国
  • 起止时间:
    2024-01-15 至 2028-12-31
  • 项目状态:
    未结题

项目摘要

Machine learning is becoming increasingly prevalent in various aspects of our lives, including several high-stakes applications, such as finance, education, and employment. These machine learning models have shown remarkable success at learning patterns present in the historical data. However, indiscriminate learning of all patterns can sometimes lead to unintended consequences, such as perpetuating disparities based on gender, race, and other protected attributes, that can adversely affect certain groups of people. This project seeks to advance the foundations of ethical and socially-responsible machine learning by empowering users to systematically identify, explain, and mitigate the sources of disparity. Rethinking the traditional paradigm of separately addressing fairness and explainability, this research project will jointly examine fairness and explainability through a unified information-theoretic lens. Furthermore, through extensive outreach and student engagements on the social impacts of machine learning, this project aims to instill interest in mathematically-principled approaches and STEM education among undergraduate and high-school students, particularly underrepresented minority students, to spearhead the next generation of socially-responsible technology.The research project will provide a novel information-theoretic view of responsible machine learning, by leveraging a body of work in information theory called Partial Information Decomposition (PID). PID is closely tethered to the principles of Blackwell sufficiency in statistical decision theory and provides a formal way of quantifying when a random variable is “more informative” than another with respect to a target variable. Combined with estimation and optimization techniques, this project will enable us to disentangle the joint information content that several random variables share about another target variable, e.g., protected attributes such as gender, race, age, nationality, etc. Four research thrusts will be investigated: (i) Providing an information-theoretic framework for explaining sources of disparity with respect to protected attributes (gender, race, etc.); (ii) Performing systematic feature selection and representation learning with disparity control; (iii) Investigating fundamental limits with a focus on distributed and federated settings; and (iv) Validating these findings on real-world datasets in finance and education. This research will lay the foundational guiding principles for engineers and policymakers so that AI can truly bring about social good.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.
机器学习在我们生活的各个方面变得越来越普遍,包括一些高风险的应用,如金融,教育和就业。这些机器学习模型在学习历史数据中存在的模式方面取得了显着的成功。然而,不加选择地学习所有模式有时会导致意想不到的后果,例如基于性别、种族和其他受保护属性的差异永久化,这可能会对某些人群产生不利影响。该项目旨在通过使用户能够系统地识别,解释和减轻差异的来源来推进道德和社会责任机器学习的基础。本研究将透过资讯论的统一透镜,重新思考传统的公平性与可解释性分别处理的范式,共同检视公平性与可解释性。此外,通过广泛的宣传和学生参与机器学习的社会影响,该项目旨在向本科生和高中生,特别是代表性不足的少数民族学生灌输对科学原则方法和STEM教育的兴趣,以引领下一代社会责任技术。该研究项目将提供一种新的负责任机器学习的信息理论观点,通过利用信息理论中称为部分信息分解(PID)的工作。PID与统计决策理论中的Blackwell充分性原则紧密相连,并提供了一种正式的量化方法,当一个随机变量比另一个目标变量“信息量更大”时。结合估计和优化技术,该项目将使我们能够解开几个随机变量关于另一个目标变量共享的联合信息内容,例如,受保护的属性,如性别,种族,年龄,国籍等四个研究重点将进行调查:(一)提供一个信息理论框架,解释与受保护的属性(性别,种族等)的差异来源; (ii)执行系统的特征选择和表示学习与差异控制;(iii)调查基本限制,重点是分布式和联邦设置;以及(iv)验证这些发现在金融和教育的真实世界数据集。这项研究将为工程师和政策制定者奠定基本的指导原则,使人工智能真正带来社会公益。该奖项反映了NSF的法定使命,通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Sanghamitra Dutta其他文献

Can Information Flows Suggest Targets for Interventions in Neural Circuits?
信息流可以建议神经回路干预的目标吗?
Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
查询偏差是否会泄漏受保护的属性?
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
公平性和准确性之间是否需要权衡?
Model Reconstruction Using Counterfactual Explanations: Mitigating the Decision Boundary Shift
使用反事实解释重建模型:减轻决策边界转移
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Pasan Dissanayake;Sanghamitra Dutta
  • 通讯作者:
    Sanghamitra Dutta
Robust Algorithmic Recourse Under Model Multiplicity With Probabilistic Guarantees
具有概率保证的模型多重性下的鲁棒算法资源

Sanghamitra Dutta的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Sanghamitra Dutta', 18)}}的其他基金

On-Line Laser-Spectroscopy on Nuclear Isomeric States
核异构态在线激光光谱分析
  • 批准号:
    9110748
  • 财政年份:
    1991
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Standard Grant

相似国自然基金

Data-driven Recommendation System Construction of an Online Medical Platform Based on the Fusion of Information
  • 批准号:
  • 批准年份:
    2024
  • 资助金额:
    万元
  • 项目类别:
    外国青年学者研究基金项目
Exploring the Intrinsic Mechanisms of CEO Turnover and Market Reaction: An Explanation Based on Information Asymmetry
  • 批准号:
    W2433169
  • 批准年份:
    2024
  • 资助金额:
    万元
  • 项目类别:
    外国学者研究基金项目
SCIENCE CHINA Information Sciences
  • 批准号:
    61224002
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目

相似海外基金

CAREER: Towards Trustworthy Machine Learning via Learning Trustworthy Representations: An Information-Theoretic Framework
职业:通过学习可信表示实现可信机器学习:信息理论框架
  • 批准号:
    2339686
  • 财政年份:
    2024
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: Optimism in Causal Reasoning via Information-theoretic Methods
职业:通过信息论方法进行因果推理的乐观主义
  • 批准号:
    2239375
  • 财政年份:
    2023
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: Information-Theoretic Approach to Turbulence: Causality, Modeling & Control
职业:湍流的信息理论方法:因果关系、建模
  • 批准号:
    2140775
  • 财政年份:
    2021
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: Information-Theoretic and Statistical Foundations of Generative Models
职业:生成模型的信息理论和统计基础
  • 批准号:
    1942230
  • 财政年份:
    2020
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: Information Theoretic Methods in Data Structures
职业:数据结构中的信息论方法
  • 批准号:
    1844887
  • 财政年份:
    2019
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
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
  • 批准号:
    1845852
  • 财政年份:
    2019
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: Communication- Efficient Distributed Computation: Information- Theoretic Foundations and Algorithms
职业:通信高效分布式计算:信息理论基础和算法
  • 批准号:
    1651492
  • 财政年份:
    2017
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: Information-Theoretic Methods for RNA Analytics
职业:RNA 分析的信息理论方法
  • 批准号:
    1651236
  • 财政年份:
    2017
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: An Information Theoretic Perspective of Consistent Distributed Storage Systems
职业:一致分布式存储系统的信息论视角
  • 批准号:
    1553248
  • 财政年份:
    2016
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
CAREER: An Information-Theoretic Approach to Communication-Constrained Statistical Learning
职业:通信受限统计学习的信息论方法
  • 批准号:
    1254041
  • 财政年份:
    2013
  • 资助金额:
    $ 66.56万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了