{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/towards-better-understanding-of-gradient","title":"Towards better understanding of gradient-based attribution methods for Deep Neural Networks","arxiv_id":"1711.06104","date":"2017-11-16","proceeding":"ICLR 2018 1","authors":["Marco Ancona","Enea Ceolini","Cengiz Öztireli","Markus Gross"],"abstract":"Understanding the flow of information in Deep Neural Networks (DNNs) is a\nchallenging problem that has gain increasing attention over the last few years.\nWhile several methods have been proposed to explain network predictions, there\nhave been only a few attempts to compare them from a theoretical perspective.\nWhat is more, no exhaustive empirical comparison has been performed in the\npast. In this work, we analyze four gradient-based attribution methods and\nformally prove conditions of equivalence and approximation between them. By\nreformulating two of these methods, we construct a unified framework which\nenables a direct comparison, as well as an easier implementation. Finally, we\npropose a novel evaluation metric, called Sensitivity-n and test the\ngradient-based attribution methods alongside with a simple perturbation-based\nattribution method on several datasets in the domains of image and text\nclassification, using various network architectures.","url_abs":"http://arxiv.org/abs/1711.06104v4","url_pdf":"http://arxiv.org/pdf/1711.06104v4.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":"towards-better-understanding-of-gradient","repo_url":"https://github.com/kundajelab/deeplift","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"towards-better-understanding-of-gradient","repo_url":"https://github.com/pytorch/captum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.06104","atlas_url":"https://app.syntology.ai/?focus=1711.06104","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1711.06104"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.06104\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.06104"},"call":"get_concepts_for_paper(arxiv_id=\"1711.06104\")"}],"by_repo":[{"repo":"kundajelab/deeplift","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pytorch/captum","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2304.11327"],"harvested_for_calls":[{"arxiv_id":"2304.11327","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.11327"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.11327\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1787f0152e7ed5cc3356aa8b2f189eca287c1b5b3da354d07921840b50f472ac","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}