{"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/global-model-interpretation-via-recursive","title":"Global Model Interpretation via Recursive Partitioning","arxiv_id":"1802.04253","date":"2018-02-11","proceeding":null,"authors":["Chengliang Yang","Anand Rangarajan","Sanjay Ranka"],"abstract":"In this work, we propose a simple but effective method to interpret black-box\nmachine learning models globally. That is, we use a compact binary tree, the\ninterpretation tree, to explicitly represent the most important decision rules\nthat are implicitly contained in the black-box machine learning models. This\ntree is learned from the contribution matrix which consists of the\ncontributions of input variables to predicted scores for each single\nprediction. To generate the interpretation tree, a unified process recursively\npartitions the input variable space by maximizing the difference in the average\ncontribution of the split variable between the divided spaces. We demonstrate\nthe effectiveness of our method in diagnosing machine learning models on\nmultiple tasks. Also, it is useful for new knowledge discovery as such insights\nare not easily identifiable when only looking at single predictions. In\ngeneral, our work makes it easier and more efficient for human beings to\nunderstand machine learning models.","url_abs":"http://arxiv.org/abs/1802.04253v2","url_pdf":"http://arxiv.org/pdf/1802.04253v2.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":"global-model-interpretation-via-recursive","repo_url":"https://github.com/west-gates/GIRP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04253","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}