{"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/understanding-learned-models-by-identifying","title":"Understanding Learned Models by Identifying Important Features at the Right Resolution","arxiv_id":"1811.07279","date":"2018-11-18","proceeding":null,"authors":["Kyubin Lee","Akshay Sood","Mark Craven"],"abstract":"In many application domains, it is important to characterize how complex\nlearned models make their decisions across the distribution of instances. One\nway to do this is to identify the features and interactions among them that\ncontribute to a model's predictive accuracy. We present a model-agnostic\napproach to this task that makes the following specific contributions. Our\napproach (i) tests feature groups, in addition to base features, and tries to\ndetermine the level of resolution at which important features can be\ndetermined, (ii) uses hypothesis testing to rigorously assess the effect of\neach feature on the model's loss, (iii) employs a hierarchical approach to\ncontrol the false discovery rate when testing feature groups and individual\nbase features for importance, and (iv) uses hypothesis testing to identify\nimportant interactions among features and feature groups. We evaluate our\napproach by analyzing random forest and LSTM neural network models learned in\ntwo challenging biomedical applications.","url_abs":"http://arxiv.org/abs/1811.07279v2","url_pdf":"http://arxiv.org/pdf/1811.07279v2.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":"understanding-learned-models-by-identifying","repo_url":"https://github.com/Craven-Biostat-Lab/mihifepe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"hypothesis-testing","task_name":"Two-sample testing"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.07279","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}