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
发表信息:
Machine Learning and Knowledge Extraction, eds. Andreas Holzinger, Peter Kieseberg, A Min Tjoa, Edgar Weippl, Lecture Notes in Computer Science 12844, Springer, pp. 79-99, 2021
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.
Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration
University of Ioannina(伊奥安纳大学);Archimedes / Athena RC Greece(阿基米德/亚特兰蒂斯研究所以及希腊);Freie Universität Berlin(柏林自由大学);Universität der Bundeswehr München(联邦国防军大学慕尼黑)
Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning System Decisions
Universiti Teknologi PETRONAS(国油科技大学);Abubakar Tafawa Balewa University(阿布巴卡尔·塔法瓦·巴莱瓦大学);Universiti Brunei Darussalam(文莱达鲁萨兰国大学);Western University(韦仕敦大学);Yale-NUS College(耶鲁-新加坡国立大学学院)
Explaining Group Recommendations via Counterfactuals
Data Science Research Centre, Tampere University Tampere Finland;Hellenic Mediterranean University \& Archimedes/Athena RC Greece;Data Science Research Centre, Tampere University;Hellenic Mediterranean University \& Archimedes/Athena RC
Beyond One-Size-Fits-All: Adapting Counterfactual Explanations to User Objectives
National Technical University of Athens(雅典国立技术大学);School of Electrical and Computer Engineering(电气与计算机工程学院);Artificial Intelligence and Learning Systems Laboratory(人工智能与学习系统实验室)