{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/abduction-based-explanations-for-machine","title":"Abduction-Based Explanations for Machine Learning Models","arxiv_id":"1811.10656","date":"2018-11-26","proceeding":null,"authors":["Alexey Ignatiev","Nina Narodytska","Joao Marques-Silva"],"abstract":"The growing range of applications of Machine Learning (ML) in a multitude of\nsettings motivates the ability of computing small explanations for predictions\nmade. Small explanations are generally accepted as easier for human decision\nmakers to understand. Most earlier work on computing explanations is based on\nheuristic approaches, providing no guarantees of quality, in terms of how close\nsuch solutions are from cardinality- or subset-minimal explanations. This paper\ndevelops a constraint-agnostic solution for computing explanations for any ML\nmodel. The proposed solution exploits abductive reasoning, and imposes the\nrequirement that the ML model can be represented as sets of constraints using\nsome target constraint reasoning system for which the decision problem can be\nanswered with some oracle. The experimental results, obtained on well-known\ndatasets, validate the scalability of the proposed approach as well as the\nquality of the computed solutions.","url_abs":"http://arxiv.org/abs/1811.10656v1","url_pdf":"http://arxiv.org/pdf/1811.10656v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"abduction-based-explanations-for-machine","repo_url":"https://github.com/alexeyignatiev/xplainer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10656","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}