SHF: Medium: Fairness in Software Systems

SHF：中：软件系统的公平性

• 批准号: 1763423
• 负责人: Yuriy Brun
• 金额: $ 105万
• 依托单位: University of Massachusetts Amherst
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-15 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1763423&HistoricalAwards=false
• 关键词: SHF; Medium; Fairness; Software; Systems

Software impacts society in many ways and increasingly automates decision-making. For example, software transcribes videos, translates documents, selects what news articles are promoted, and determines who gets a loan or gets hired. It is possible for software to exhibit bias in its operation, whether or not it is intended by the customers or developers of the software. For example, software might be more accurate at transcribing male voices than female ones. Or software may inject societal stereotypes into automated translations, and risk-assessment computations may exhibit racial bias. As more societal functions operate in cyberspace, the importance of software fairness increases. In these settings, data-driven software has the ability to shape human behavior: it affects the products we view and purchase, the news articles we read, the social interactions we engage in, and, ultimately, the opinions we form. Biases in data and software risk forming, propagating, and perpetuating biases in society. This project develops theory, techniques and tools to enable software designers and engineers to describe fairness requirements, test the software for fairness properties, and debug fairness defects. The outcomes of this project will help increase the society's trust in software decisions and in the data the software uses, in turn, increasing potential impact and benefits the software can bring to society.The project addresses scientific questions behind efficiently and effectively measuring potential bias and helping stakeholders make informed decisions about software. It is not the project's aim to devise policies or eliminate bias in software. Instead, the aim is to provide software testing tools and measures that can be validated for formally specified software fairness properties. To measure bias, the project develops a novel approach for measuring causal relationships between program inputs and outputs. Software testing enables conducting causal experiments consisting of running the software with nearly identical inputs that vary only in a key input characteristic under test. Variations in an input characteristic that affect execution behavior provide evidence of a causal relationship. The project identifies when causal relationships are appropriate for measuring potential bias, develops efficient testing methods for measuring these relationships, and creates tools and techniques to help engineers identify and modify the causes of these relationships.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.

软件以多种方式影响社会，并日益自动化决策。例如，软件转录视频、翻译文档、选择要宣传的新闻文章以及确定谁获得贷款或被雇用。软件在其操作中可能会表现出偏差，无论软件的客户或开发人员是否有意为之。例如，软件在转录男性声音方面可能比转录女性声音更准确。或者软件可能会将社会刻板印象注入自动翻译中，并且风险评估计算可能会表现出种族偏见。随着越来越多的社会功能在网络空间中运作，软件公平的重要性也随之增加。在这些环境中，数据驱动的软件能够塑造人类行为：它影响我们查看和购买的产品、我们阅读的新闻文章、我们参与的社交互动，以及最终我们形成的观点。数据和软件中的偏见有可能在社会中形成、传播和延续偏见。该项目开发理论、技术和工具，使软件设计人员和工程师能够描述公平性要求、测试软件的公平性属性以及调试公平性缺陷。该项目的成果将有助于提高社会对软件决策和软件使用的数据的信任，进而增加软件可以给社会带来的潜在影响和利益。该项目解决了高效、有效地衡量潜在偏见和风险背后的科学问题。帮助利益相关者做出有关软件的明智决策。该项目的目的不是制定政策或消除软件中的偏见。相反，目的是提供可以验证正式指定的软件公平性属性的软件测试工具和措施。为了衡量偏差，该项目开发了一种新方法来衡量程序输入和输出之间的因果关系。软件测试可以进行因果实验，包括使用几乎相同的输入运行软件，这些输入仅在被测的关键输入特性上有所不同。影响执行行为的输入特征的变化提供了因果关系的证据。该项目确定因果关系何时适合测量潜在偏差，开发有效的测试方法来测量这些关系，并创建工具和技术来帮助工程师识别和修改这些关系的原因。该奖项反映了 NSF 的法定使命，并被认为是值得的通过使用基金会的智力优势和更广泛的影响审查标准进行评估来获得支持。

项目成果

CoCo: Interactive Exploration of Conformance Constraints for Data Understanding and Data Cleaning

CoCo：数据理解和数据清理的一致性约束的交互式探索

• DOI: 10.1145/3448016.3452750
• 发表时间: 2021
• 期刊: International Conference on Management of Data (SIGMOD
• 作者: Fariha, Anna;Tiwari, Ashish;Meliou, Alexandra;Radhakrishna, Arjun;Gulwani, Sumit
• 通讯作者: Gulwani, Sumit

Explain 3D: explaining disagreements in disjoint datasets

解释 3D：解释不相交数据集中的分歧

• DOI: 10.14778/3317315.3317320
• 发表时间: 2019
• 期刊: Proceedings of the VLDB Endowment
• 影响因子: 2.5
• 作者: Wang, Xiaolan;Meliou, Alexandra
• 通讯作者: Meliou, Alexandra

Fairkit-learn: A Fairness Evaluation and Comparison Toolkit

Fairkit-learn：公平性评估和比较工具包

• DOI: 10.1145/3510454.3516830
• 发表时间: 2022
• 期刊: Proceedings of the Demonstrations Track at the 44th International Conference on Software Engineering (ICSE
• 作者: Johnson, Brittany;Brun, Yuriy
• 通讯作者: Brun, Yuriy

Software Fairness

• DOI: 10.1145/3236024.3264838
• 发表时间: 2018-01-01
• 期刊: ESEC/FSE'18: PROCEEDINGS OF THE 2018 26TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING
• 作者: Brun, Yuriy;Meliou, Alexandra
• 通讯作者: Meliou, Alexandra

Improved Approximation and Scalability for Fair Max-Min Diversification

• DOI: 10.4230/lipics.icdt.2022.7
• 发表时间: 2022-01
• 期刊: Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases
• 作者: Raghavendra Addanki;A. Mcgregor;A. Meliou;Zafeiria Moumoulidou