The Fairness, Accountability, and Transparency (FAccT) literature tends to focus on bias as a problem that requires ex post solutions (e.g. fairness metrics), rather than addressing the underlying social and technical conditions that (re)produce it. In this article, we propose a complementary strategy that uses genealogy as a constructive, epistemic critique to explain algorithmic bias in terms of the conditions that enable it. We focus on XAI feature attributions (Shapley values) and counterfactual approaches as potential tools to gauge these conditions and offer two main contributions. One is constructive: we develop a theoretical framework to classify these approaches according to their relevance for bias as evidence of social disparities. We draw on Pearl’s ladder of causation (Causality: models, reasoning, and inference. Cambridge University Press, Cambridge, 2000, Causality, 2nd edn. Cambridge University Press, Cambridge, 2009. https://doi.org/10.1017/CBO9780511803161) to order these XAI approaches concerning their ability to answer fairness-relevant questions and identify fairness-relevant solutions. The other contribution is critical: we evaluate these approaches in terms of their assumptions about the role of protected characteristics in discriminatory outcomes. We achieve this by building on Kohler-Hausmann’s (Northwest Univ Law Rev 113(5):1163–1227, 2019) constructivist theory of discrimination. We derive three recommendations for XAI practitioners to develop and AI policymakers to regulate tools that address algorithmic bias in its conditions and hence mitigate its future occurrence.
公平、问责和透明（FAccT）文献倾向于将偏差作为一个需要事后解决方案（如公平度量）的问题来关注，而不是解决（再）产生偏差的潜在社会和技术条件。在本文中，我们提出了一种补充策略，将谱系学作为一种建设性的认识论批判，从促成算法偏差的条件来解释算法偏差。我们将重点放在 XAI 特征归因（夏普利值）和反事实方法上，将其作为衡量这些条件的潜在工具，并提供两个主要贡献。其一是建设性的：我们建立了一个理论框架，根据这些方法与作为社会差异证据的偏见的相关性对其进行分类。我们借鉴了珀尔的因果关系阶梯（《因果关系：模型、推理和推论》。剑桥大学出版社，剑桥，2000 年，《因果关系》，第二版。https://doi.org/10.1017/CBO9780511803161)，对这些 XAI 方法回答公平相关问题和确定公平相关解决方案的能力进行排序。另一个重要贡献是：我们根据这些方法对受保护特征在歧视性结果中所起作用的假设，对其进行评估。为此，我们以科勒-豪斯曼（Northwest Univ Law Rev 113(5):1163-1227, 2019）的歧视建构主义理论为基础。我们得出了三项建议，供 XAI 从业人员开发和 AI 政策制定者规范工具，以解决算法偏见的条件，从而减少其未来的发生。
{"title":"A Genealogical Approach to Algorithmic Bias","authors":"M. Ziosi, David Watson, Luciano Floridi","doi":"10.2139/ssrn.4734082","DOIUrl":"https://doi.org/10.2139/ssrn.4734082","url":null,"abstract":"The Fairness, Accountability, and Transparency (FAccT) literature tends to focus on bias as a problem that requires ex post solutions (e.g. fairness metrics), rather than addressing the underlying social and technical conditions that (re)produce it. In this article, we propose a complementary strategy that uses genealogy as a constructive, epistemic critique to explain algorithmic bias in terms of the conditions that enable it. We focus on XAI feature attributions (Shapley values) and counterfactual approaches as potential tools to gauge these conditions and offer two main contributions. One is constructive: we develop a theoretical framework to classify these approaches according to their relevance for bias as evidence of social disparities. We draw on Pearl’s ladder of causation (Causality: models, reasoning, and inference. Cambridge University Press, Cambridge, 2000, Causality, 2nd edn. Cambridge University Press, Cambridge, 2009. https://doi.org/10.1017/CBO9780511803161) to order these XAI approaches concerning their ability to answer fairness-relevant questions and identify fairness-relevant solutions. The other contribution is critical: we evaluate these approaches in terms of their assumptions about the role of protected characteristics in discriminatory outcomes. We achieve this by building on Kohler-Hausmann’s (Northwest Univ Law Rev 113(5):1163–1227, 2019) constructivist theory of discrimination. We derive three recommendations for XAI practitioners to develop and AI policymakers to regulate tools that address algorithmic bias in its conditions and hence mitigate its future occurrence.","PeriodicalId":404219,"journal":{"name":"Minds Mach.","volume":"5 12","pages":"9"},"PeriodicalIF":0.0,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141020513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：