{"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/rule-induction-for-global-explanation-of","title":"Rule induction for global explanation of trained models","arxiv_id":"1808.09744","date":"2018-08-29","proceeding":"WS 2018 11","authors":["Madhumita Sushil","Simon Šuster","Walter Daelemans"],"abstract":"Understanding the behavior of a trained network and finding explanations for\nits outputs is important for improving the network's performance and\ngeneralization ability, and for ensuring trust in automated systems. Several\napproaches have previously been proposed to identify and visualize the most\nimportant features by analyzing a trained network. However, the relations\nbetween different features and classes are lost in most cases. We propose a\ntechnique to induce sets of if-then-else rules that capture these relations to\nglobally explain the predictions of a network. We first calculate the\nimportance of the features in the trained network. We then weigh the original\ninputs with these feature importance scores, simplify the transformed input\nspace, and finally fit a rule induction model to explain the model predictions.\nWe find that the output rule-sets can explain the predictions of a neural\nnetwork trained for 4-class text classification from the 20 newsgroups dataset\nto a macro-averaged F-score of 0.80. We make the code available at\nhttps://github.com/clips/interpret_with_rules.","url_abs":"http://arxiv.org/abs/1808.09744v1","url_pdf":"http://arxiv.org/pdf/1808.09744v1.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":"rule-induction-for-global-explanation-of","repo_url":"https://github.com/clips/interpret_with_rules","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09744","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}