{"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/inverse-classification-for-comparison-based","title":"Inverse Classification for Comparison-based Interpretability in Machine Learning","arxiv_id":"1712.08443","date":"2017-12-22","proceeding":null,"authors":["Thibault Laugel","Marie-Jeanne Lesot","Christophe Marsala","Xavier Renard","Marcin Detyniecki"],"abstract":"In the context of post-hoc interpretability, this paper addresses the task of\nexplaining the prediction of a classifier, considering the case where no\ninformation is available, neither on the classifier itself, nor on the\nprocessed data (neither the training nor the test data). It proposes an\ninstance-based approach whose principle consists in determining the minimal\nchanges needed to alter a prediction: given a data point whose classification\nmust be explained, the proposed method consists in identifying a close\nneighbour classified differently, where the closeness definition integrates a\nsparsity constraint. This principle is implemented using observation generation\nin the Growing Spheres algorithm. Experimental results on two datasets\nillustrate the relevance of the proposed approach that can be used to gain\nknowledge about the classifier.","url_abs":"http://arxiv.org/abs/1712.08443v1","url_pdf":"http://arxiv.org/pdf/1712.08443v1.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":"inverse-classification-for-comparison-based","repo_url":"https://github.com/carla-recourse/CARLA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"inverse-classification-for-comparison-based","repo_url":"https://github.com/thibaultlaugel/growingspheres","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"inverse-classification-for-comparison-based","repo_url":"https://github.com/wangyongjie-ntu/CFAI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"inverse-classification-for-comparison-based","repo_url":"https://github.com/wangyongjie-ntu/Counterfactual-Explanations-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.08443","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}