{"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/variance-based-feature-importance-in-neural","title":"Variance-Based Feature Importance in Neural Networks","arxiv_id":null,"date":"2019-10-16","proceeding":null,"authors":["Cláudio Rebelo de Sá"],"abstract":"This paper proposes a new method to measure the relative importance of features in Artificial Neural Networks (ANN) models. Its underlying principle assumes that the more important a feature is, the more the weights, connected to the respective input neuron, will change during the training of the model. To capture this behavior, a running variance of every weight connected to the input layer is measured during training. For that, an adaptation of Welford’s online algorithm for computing the online variance is proposed. When the training is finished, for each input, the variances of the weights are combined with the final weights to obtain the measure of relative importance for each feature. This method was tested with shallow and deep neural network architectures on several well-known classification and regression problems. The results obtained confirm that this approach is making meaningful measurements. Moreover, results showed that the importance scores are highly correlated with the variable importance method from Random Forests (RF).","url_abs":"https://link.springer.com/chapter/10.1007/978-3-030-33778-0_24","url_pdf":"https://link.springer.com/chapter/10.1007/978-3-030-33778-0_24","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":"variance-based-feature-importance-in-neural","repo_url":"https://github.com/rebelosa/feature-importance-neural-networks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[{"method_slug":"varimpviann","method_name":"VarImpVIANN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"varimpviann","name":"VarImpVIANN","full_name":"Variance-based Feature Importance of Artificial Neural Networks"}],"results":[{"leaderboard":"/sota/feature-importance-on-breastcancer","task":"Feature Importance","dataset":"Breastcancer","model":"VarImpVIANN","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.60"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-breastcancer","task":"Feature Importance","dataset":"Breastcancer","model":"Garson Variable Importance","rank_in_archive_order":2,"of":2,"metrics":{"Pearson Correlation":"0.22"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-diabetes","task":"Feature Importance","dataset":"Diabetes","model":"VarImpVIANN","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.86"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-diabetes","task":"Feature Importance","dataset":"Diabetes","model":"Garson Variable Importance","rank_in_archive_order":2,"of":2,"metrics":{"Pearson Correlation":"0.64"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-digits","task":"Feature Importance","dataset":"Digits","model":"VarImpVIANN","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.83"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-digits","task":"Feature Importance","dataset":"Digits","model":"Garson Variable Importance","rank_in_archive_order":2,"of":2,"metrics":{"Pearson Correlation":"0.60"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-wine","task":"Feature Importance","dataset":"Wine","model":"Garson Variable Importance","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.74"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-wine","task":"Feature Importance","dataset":"Wine","model":"VarImpVIANN","rank_in_archive_order":2,"of":2,"metrics":{"Pearson Correlation":"0.41"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-boston","task":"Feature Importance","dataset":"boston","model":"VarImpVIANN","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.76"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-boston","task":"Feature Importance","dataset":"boston","model":"Garson Variable Importance","rank_in_archive_order":2,"of":2,"metrics":{"Pearson Correlation":"0.76"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-iris","task":"Feature Importance","dataset":"iris","model":"VarImpVIANN","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.90"},"uses_additional_data":false},{"leaderboard":"/sota/feature-importance-on-iris","task":"Feature Importance","dataset":"iris","model":"Garson Variable Importance","rank_in_archive_order":2,"of":2,"metrics":{"Pearson Correlation":"0.73"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"rebelosa/feature-importance-neural-networks","kind":"official","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":"b6197a3d5c555e21c2eff2677942b36f7d5afe64f1b2614bbd325d4254d2a16a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}