{"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/feature-importance-measure-for-non-linear","title":"Feature Importance Measure for Non-linear Learning Algorithms","arxiv_id":"1611.07567","date":"2016-11-22","proceeding":null,"authors":["Marina M. -C. Vidovic","Nico Görnitz","Klaus-Robert Müller","Marius Kloft"],"abstract":"Complex problems may require sophisticated, non-linear learning methods such\nas kernel machines or deep neural networks to achieve state of the art\nprediction accuracies. However, high prediction accuracies are not the only\nobjective to consider when solving problems using machine learning. Instead,\nparticular scientific applications require some explanation of the learned\nprediction function. Unfortunately, most methods do not come with out of the\nbox straight forward interpretation. Even linear prediction functions are not\nstraight forward to explain if features exhibit complex correlation structure.\n  In this paper, we propose the Measure of Feature Importance (MFI). MFI is\ngeneral and can be applied to any arbitrary learning machine (including kernel\nmachines and deep learning). MFI is intrinsically non-linear and can detect\nfeatures that by itself are inconspicuous and only impact the prediction\nfunction through their interaction with other features. Lastly, MFI can be used\nfor both --- model-based feature importance and instance-based feature\nimportance (i.e, measuring the importance of a feature for a particular data\npoint).","url_abs":"http://arxiv.org/abs/1611.07567v1","url_pdf":"http://arxiv.org/pdf/1611.07567v1.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":"feature-importance-measure-for-non-linear","repo_url":"https://github.com/mcvidomi/MFI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.07567","atlas_url":"https://app.syntology.ai/?focus=1611.07567","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":"1611.07567"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1611.07567\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1611.07567"},"call":"get_concepts_for_paper(arxiv_id=\"1611.07567\")"}],"by_repo":[{"repo":"mcvidomi/MFI","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"f9e57bd3bc814c37a97a0a13a7454cecab15d3f32f2ecfd8969d7715f188b6d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}