{"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/a-workflow-for-visual-diagnostics-of-binary","title":"A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations","arxiv_id":"1705.01968","date":"2017-05-04","proceeding":null,"authors":["Josua Krause","Aritra Dasgupta","Jordan Swartz","Yindalon Aphinyanaphongs","Enrico Bertini"],"abstract":"Human-in-the-loop data analysis applications necessitate greater transparency\nin machine learning models for experts to understand and trust their decisions.\nTo this end, we propose a visual analytics workflow to help data scientists and\ndomain experts explore, diagnose, and understand the decisions made by a binary\nclassifier. The approach leverages \"instance-level explanations\", measures of\nlocal feature relevance that explain single instances, and uses them to build a\nset of visual representations that guide the users in their investigation. The\nworkflow is based on three main visual representations and steps: one based on\naggregate statistics to see how data distributes across correct / incorrect\ndecisions; one based on explanations to understand which features are used to\nmake these decisions; and one based on raw data, to derive insights on\npotential root causes for the observed patterns. The workflow is derived from a\nlong-term collaboration with a group of machine learning and healthcare\nprofessionals who used our method to make sense of machine learning models they\ndeveloped. The case study from this collaboration demonstrates that the\nproposed workflow helps experts derive useful knowledge about the model and the\nphenomena it describes, thus experts can generate useful hypotheses on how a\nmodel can be improved.","url_abs":"http://arxiv.org/abs/1705.01968v3","url_pdf":"http://arxiv.org/pdf/1705.01968v3.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":"a-workflow-for-visual-diagnostics-of-binary","repo_url":"https://github.com/nyuvis/explanation_explorer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.01968","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}