Abstraction, validation, and generalization for explainable artificial intelligence. Issue 4 (12th September 2021)

• Record Type: Journal Article
• Authors: Yang, Scott Cheng‐Hsin; Folke, Tomas; Shafto, Patrick
• Other Names: Gunning Dave guestEditor.; Vorm Eric guestEditor.; Wang Jennifer Yunyan guestEditor.; Turek Matt guestEditor.
• Is Part Of: Applied AI Letters. Volume 2:Issue 4(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-09-12
• Subjects: Bayesian Teaching -- cognitive science -- design patterns -- explainable AI -- human computer interaction; 006.3
• DOI: 10.1002/ail2.37
• Languages: English
• ISSNs: 2689-5595

Abstract

Abstract: Neural network architectures are achieving superhuman performance on an expanding range of tasks. To effectively and safely deploy these systems, their decision‐making must be understandable to a wide range of stakeholders. Methods to explain artificial intelligence (AI) have been proposed to answer this challenge, but a lack of theory impedes the development of systematic abstractions, which are necessary for cumulative knowledge gains. We propose Bayesian Teaching as a framework for unifying explainable AI (XAI) by integrating machine learning and human learning. Bayesian Teaching formalizes explanation as a communication act of an explainer to shift the beliefs of an explainee. This formalization decomposes a wide range of XAI methods into four components: (a) the target inference, (b) the explanation, (c) the explainee model, and (d) the explainer model. The abstraction afforded by Bayesian Teaching to decompose XAI methods elucidates the invariances among them. The decomposition of XAI systems enables modular validation, as each of the first three components listed can be tested semi‐independently. This decomposition also promotes generalization through recombination of components from different XAI systems, which facilitates the generation of novel variants. These new variants need not be evaluated one by one provided that each component has been validated, leading to an exponential decrease in development time. Finally, by making the goal of explanation explicit, Bayesian Teaching helps developers to assess how suitable an XAI system is for its intended real‐world use case. Thus, Bayesian Teaching provides a theoretical framework that encourages systematic, scientific investigation of XAI. Abstract : We propose Bayesian Teaching as a framework for unifying explainable AI (XAI). Bayesian Teaching introduces a collection of abstractions that facilitate decomposition of prior approaches and support systematic validation of components. We argue that abstraction and validation together support generalization—the ability to recompose validated aspects of models into new XAI methods for rapid deployment on new tasks and domains.