{"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/not-just-a-black-box-learning-important","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","arxiv_id":"1605.01713","date":"2016-05-05","proceeding":null,"authors":["Avanti Shrikumar","Peyton Greenside","Anna Shcherbina","Anshul Kundaje"],"abstract":"Note: This paper describes an older version of DeepLIFT. See\nhttps://arxiv.org/abs/1704.02685 for the newer version. Original abstract\nfollows: The purported \"black box\" nature of neural networks is a barrier to\nadoption in applications where interpretability is essential. Here we present\nDeepLIFT (Learning Important FeaTures), an efficient and effective method for\ncomputing importance scores in a neural network. DeepLIFT compares the\nactivation of each neuron to its 'reference activation' and assigns\ncontribution scores according to the difference. We apply DeepLIFT to models\ntrained on natural images and genomic data, and show significant advantages\nover gradient-based methods.","url_abs":"http://arxiv.org/abs/1605.01713v3","url_pdf":"http://arxiv.org/pdf/1605.01713v3.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":"not-just-a-black-box-learning-important","repo_url":"https://github.com/pytorch/captum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.01713","atlas_url":"https://app.syntology.ai/?focus=1605.01713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}