{"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/the-intriguing-properties-of-model","title":"The Intriguing Properties of Model Explanations","arxiv_id":"1801.09808","date":"2018-01-30","proceeding":null,"authors":["Maruan Al-Shedivat","Avinava Dubey","Eric P. Xing"],"abstract":"Linear approximations to the decision boundary of a complex model have become\none of the most popular tools for interpreting predictions. In this paper, we\nstudy such linear explanations produced either post-hoc by a few recent methods\nor generated along with predictions with contextual explanation networks\n(CENs). We focus on two questions: (i) whether linear explanations are always\nconsistent or can be misleading, and (ii) when integrated into the prediction\nprocess, whether and how explanations affect the performance of the model. Our\nanalysis sheds more light on certain properties of explanations produced by\ndifferent methods and suggests that learning models that explain and predict\njointly is often advantageous.","url_abs":"http://arxiv.org/abs/1801.09808v1","url_pdf":"http://arxiv.org/pdf/1801.09808v1.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":"the-intriguing-properties-of-model","repo_url":"https://github.com/alshedivat/cen","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}