arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.07578cs.AI
收藏

充分和公正的解释

Adequate and fair explanations

IRIT, Université Paul Sabatier(IRIT,保罗·萨巴捷大学);Telindus;Amazon Research(亚马逊研究院)

Nicholas Asher, Soumya Paul, Chris Russell

摘要:

解释复杂的基于机器学习的系统是人工智能基础的一个重要问题。最近的努力显示了提供解释的各种方法。这些方法可以大致分为两个流派:那些提供本地和人类可解释的近似机器学习算法的方法,以及逻辑方法,精确地解释决策的一个方面。在本文中,我们集中在第二个学校的确切解释与严格的逻辑基础。这些精确的方法有一个认识论问题。虽然它们可以提供完整的解释,但这种解释可能太复杂,人类无法理解,甚至无法以人类可读的形式写下来。可解释性需要在认识上可理解的解释,人类可以理解的解释。然而,什么是一个足够完整的认识上可理解的解释仍然需要澄清。我们在这里这样做的反事实,以下[Wachter等人,2017年]。在反事实解释中,提供完整解释所需的许多假设都是隐含的。为此,反事实解释利用特定数据点或样本的属性,因此也是局部和部分解释。我们探讨如何从局部局部解释,我们称之为完整的局部解释,然后到全球的。但是为了保持可访问性,我们主张需要可访问性。这使得它有可能隐藏明确的偏见存在于算法中,可能是有害的或不公平的。我们调查它是多么容易发现这些偏见,在提供完整和公平的解释,利用结构的反事实集提供一个完整的本地解释。

英文摘要:

Explaining sophisticated machine-learning based systems is an important issue at the foundations of AI. Recent efforts have shown various methods for providing explanations. These approaches can be broadly divided into two schools: those that provide a local and human interpreatable approximation of a machine learning algorithm, and logical approaches that exactly characterise one aspect of the decision. In this paper we focus upon the second school of exact explanations with a rigorous logical foundation. There is an epistemological problem with these exact methods. While they can furnish complete explanations, such explanations may be too complex for humans to understand or even to write down in human readable form. Interpretability requires epistemically accessible explanations, explanations humans can grasp. Yet what is a sufficiently complete epistemically accessible explanation still needs clarification. We do this here in terms of counterfactuals, following [Wachter et al., 2017]. With counterfactual explanations, many of the assumptions needed to provide a complete explanation are left implicit. To do so, counterfactual explanations exploit the properties of a particular data point or sample, and as such are also local as well as partial explanations. We explore how to move from local partial explanations to what we call complete local explanations and then to global ones. But to preserve accessibility we argue for the need for partiality. This partiality makes it possible to hide explicit biases present in the algorithm that may be injurious or unfair.We investigate how easy it is to uncover these biases in providing complete and fair explanations by exploiting the structure of the set of counterfactuals providing a complete local explanation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑