{"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/streaming-weak-submodularity-interpreting","title":"Streaming Weak Submodularity: Interpreting Neural Networks on the Fly","arxiv_id":"1703.02647","date":"2017-03-08","proceeding":"NeurIPS 2017 12","authors":["Ethan R. Elenberg","Alexandros G. Dimakis","Moran Feldman","Amin Karbasi"],"abstract":"In many machine learning applications, it is important to explain the\npredictions of a black-box classifier. For example, why does a deep neural\nnetwork assign an image to a particular class? We cast interpretability of\nblack-box classifiers as a combinatorial maximization problem and propose an\nefficient streaming algorithm to solve it subject to cardinality constraints.\nBy extending ideas from Badanidiyuru et al. [2014], we provide a constant\nfactor approximation guarantee for our algorithm in the case of random stream\norder and a weakly submodular objective function. This is the first such\ntheoretical guarantee for this general class of functions, and we also show\nthat no such algorithm exists for a worst case stream order. Our algorithm\nobtains similar explanations of Inception V3 predictions $10$ times faster than\nthe state-of-the-art LIME framework of Ribeiro et al. [2016].","url_abs":"http://arxiv.org/abs/1703.02647v3","url_pdf":"http://arxiv.org/pdf/1703.02647v3.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":"streaming-weak-submodularity-interpreting","repo_url":"https://github.com/eelenberg/streak","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"lime","method_name":"LIME"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.02647","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}