Algorithmic Transparency via Quantitative Input Influence
Algorithmic Transparency via Quantitative Input Influence
复制标题
DOI：
10.1007/978-3-319-54024-5_4
复制
发表时间：
2017-01-01
期刊：
影响因子：
--
通讯作者：
Zick, Yair
中科院分区：
文献类型：
--
作者：
Datta, Anupam;Sen, Shayak;Zick, Yair
采用机器学习的算法系统往往不透明——很难解释为什么会做出某个决策。我们提出了一个正式的基础，以提高此类决策系统的透明度。具体来说，我们引入了一系列定量输入影响（QII）度量，用于捕捉输入对系统输出的影响程度。这些度量为设计伴随系统决策的透明度报告（例如，解释一个特定的信贷决策）以及为对内部和外部监督有用的测试工具（例如，检测算法歧视）提供了基础。独特的是，我们的因果QII度量在测量影响时仔细考虑了相关输入。它们支持一类通用的透明度查询，尤其可以解释关于个人和群体的决策。最后，由于单个输入可能并不总是具有高影响力，QII度量还使用诸如夏普利值等有原则的聚合度量来量化一组输入（例如年龄和收入）对结果（例如贷款决策）的联合影响以及该组内单个输入（例如收入）的平均边际影响，夏普利值先前已应用于测量投票中的影响力。
Algorithmic systems that employ machine learning are often opaque-it is difficult to explain why a certain decision was made. We present a formal foundation to improve the transparency of such decision-making systems. Specifically, we introduce a family of Quantitative Input Influence (QII) measures that capture the degree of input influence on system outputs. These measures provide a foundation for the design of transparency reports that accompany system decisions (e.g., explaining a specific credit decision) and for testing tools useful for internal and external oversight (e.g., to detect algorithmic discrimination). Distinctively, our causal QII measures carefully account for correlated inputs while measuring influence. They support a general class of transparency queries and can, in particular, explain decisions about individuals and groups. Finally, since single inputs may not always have high influence, the QII measures also quantify the joint influence of a set of inputs (e.g., age and income) on outcomes (e.g. loan decisions) and the average marginal influence of individual inputs within such a set (e.g., income) using principled aggregation measures, such as the Shapley value, previously applied to measure influence in voting.