Year: 2024
Type: conference-paper
Abstract: We focus on explaining image classifiers, taking the work of Mothilal et al. 2021 (MMTS) as our point of departure. We observe that, although MMTS claim to be using the definition of explanation proposed by Halpern 2016, they do not quite do so. Roughly speaking, Halpern’s definition has a necessity clause and a sufficiency clause. MMTS replace the necessity clause by a requirement that, as we show, implies it. Halpern’s definition also allows agents to restrict the set of options considered. While these difference may seem minor, as we show, they can have a nontrivial impact on explanations. We also show that, essentially without change, Halpern’s definition can handle two issues that have proved difficult for other approaches: explanations of absence (when, for example, an image classifier for tumors outputs “no tumor”) and explanations of rare events (such as tumors).
DOI: 10.24963/kr.2024/25
Authors: Hana Chockler, Joseph Y. Halpern
Institutions: King's College London, Cornell University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Awards: G132316624, UKRI Trustworthy Autonomous Systems Node in Governance and Regulation, FMitF: Track I: Formal Verification for Mechanism Design, Causality in Healthcare AI Hub, G2279853913, G301723715, G4526694307, G4653709976, G4683617588, UKRI Trustworthy Autonomous Systems Hub, G608057831, G7452299184, G8251700772, G8415477955, G8709435
OpenAlex ID: W4403792989