{"url":"/task/feature-importance","name":"Feature Importance","slug":"feature-importance","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":890,"papers_with_code":335,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/feature-importance-on-boston","slug":"feature-importance-on-boston","dataset":"boston","dataset_url":null,"rows_in_archive":2,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"VarImpVIANN","paper_title":"Variance-Based Feature Importance in Neural Networks","paper_url":"/paper/variance-based-feature-importance-in-neural","paper_date":"2019-10-16","arxiv_id":null,"code_links":[{"title":"rebelosa/feature-importance-neural-networks","url":"https://github.com/rebelosa/feature-importance-neural-networks"}],"syntology":null}},{"leaderboard":"/sota/feature-importance-on-breastcancer","slug":"feature-importance-on-breastcancer","dataset":"Breastcancer","dataset_url":null,"rows_in_archive":2,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"VarImpVIANN","paper_title":"Variance-Based Feature Importance in Neural Networks","paper_url":"/paper/variance-based-feature-importance-in-neural","paper_date":"2019-10-16","arxiv_id":null,"code_links":[{"title":"rebelosa/feature-importance-neural-networks","url":"https://github.com/rebelosa/feature-importance-neural-networks"}],"syntology":null}},{"leaderboard":"/sota/feature-importance-on-diabetes","slug":"feature-importance-on-diabetes","dataset":"Diabetes","dataset_url":"/dataset/diabetes","rows_in_archive":2,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"VarImpVIANN","paper_title":"Variance-Based Feature Importance in Neural Networks","paper_url":"/paper/variance-based-feature-importance-in-neural","paper_date":"2019-10-16","arxiv_id":null,"code_links":[{"title":"rebelosa/feature-importance-neural-networks","url":"https://github.com/rebelosa/feature-importance-neural-networks"}],"syntology":null}},{"leaderboard":"/sota/feature-importance-on-digits","slug":"feature-importance-on-digits","dataset":"Digits","dataset_url":"/dataset/digits","rows_in_archive":2,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"VarImpVIANN","paper_title":"Variance-Based Feature Importance in Neural Networks","paper_url":"/paper/variance-based-feature-importance-in-neural","paper_date":"2019-10-16","arxiv_id":null,"code_links":[{"title":"rebelosa/feature-importance-neural-networks","url":"https://github.com/rebelosa/feature-importance-neural-networks"}],"syntology":null}},{"leaderboard":"/sota/feature-importance-on-iris","slug":"feature-importance-on-iris","dataset":"iris","dataset_url":"/dataset/iris-1","rows_in_archive":2,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"VarImpVIANN","paper_title":"Variance-Based Feature Importance in Neural Networks","paper_url":"/paper/variance-based-feature-importance-in-neural","paper_date":"2019-10-16","arxiv_id":null,"code_links":[{"title":"rebelosa/feature-importance-neural-networks","url":"https://github.com/rebelosa/feature-importance-neural-networks"}],"syntology":null}},{"leaderboard":"/sota/feature-importance-on-wine","slug":"feature-importance-on-wine","dataset":"Wine","dataset_url":"/dataset/wine","rows_in_archive":2,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"Garson Variable Importance","paper_title":"Variance-Based Feature Importance in Neural Networks","paper_url":"/paper/variance-based-feature-importance-in-neural","paper_date":"2019-10-16","arxiv_id":null,"code_links":[{"title":"rebelosa/feature-importance-neural-networks","url":"https://github.com/rebelosa/feature-importance-neural-networks"}],"syntology":null}}],"datasets":[{"url":"/dataset/digits","name":"Digits","full_name":"Optical Recognition of Handwritten Digits","num_papers_in_archive":21},{"url":"/dataset/iris-1","name":"iris","full_name":"iris","num_papers_in_archive":20},{"url":"/dataset/wine","name":"Wine","full_name":"Wine Data Set","num_papers_in_archive":11},{"url":"/dataset/diabetes","name":"Diabetes","full_name":"Diabetes 130-US Hospitals for Years 1999-2008","num_papers_in_archive":5},{"url":"/dataset/hotel-sales","name":"Hotel","full_name":"Hospitality > Tourism > Hotel Demand/Sales","num_papers_in_archive":2},{"url":"/dataset/simply-clevr","name":"simply-CLEVR","full_name":null,"num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":335,"tagged_in_all":890,"items":[{"url":"/paper/fibinet-combining-feature-importance-and","title":"FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction","date":"2019-05-23","arxiv_id":"1905.09433","repositories_listed":31,"syntology":{"n":26,"n_ran":2,"n_unverified":24,"n_pointer_only":3}},{"url":"/paper/a-unified-approach-to-interpreting-model","title":"A Unified Approach to Interpreting Model Predictions","date":"2017-05-22","arxiv_id":"1705.07874","repositories_listed":17,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":6}},{"url":"/paper/rise-randomized-input-sampling-for","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","date":"2018-06-19","arxiv_id":"1806.07421","repositories_listed":13,"syntology":{"n":34,"n_ran":1,"n_unverified":33,"n_pointer_only":10}},{"url":"/paper/fat-deepffm-field-attentive-deep-field-aware","title":"FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine","date":"2019-05-15","arxiv_id":"1905.06336","repositories_listed":12,"syntology":null},{"url":"/paper/attention-is-not-explanation","title":"Attention is not Explanation","date":"2019-02-26","arxiv_id":"1902.10186","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/interpretable-machine-learning-definitions","title":"Interpretable machine learning: definitions, methods, and applications","date":"2019-01-14","arxiv_id":"1901.04592","repositories_listed":6,"syntology":{"n":27,"n_ran":2,"n_unverified":25,"n_pointer_only":0}},{"url":"/paper/understanding-global-feature-contributions","title":"Understanding Global Feature Contributions With Additive Importance Measures","date":"2020-04-01","arxiv_id":"2004.00668","repositories_listed":4,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/disentangled-attribution-curves-for","title":"Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees","date":"2019-05-18","arxiv_id":"1905.07631","repositories_listed":4,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/patient2vec-a-personalized-interpretable-deep","title":"Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record","date":"2018-10-10","arxiv_id":"1810.04793","repositories_listed":4,"syntology":null},{"url":"/paper/fast-nonparametric-feature-selection-with","title":"Nonparametric IPSS: Fast, flexible feature selection with false discovery control","date":"2024-10-03","arxiv_id":"2410.02208","repositories_listed":3,"syntology":null},{"url":"/paper/hospital-length-of-stay-prediction-based-on","title":"Interpretable machine learning for time-to-event prediction in medicine and healthcare","date":"2023-03-17","arxiv_id":"2303.09817","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/positive-unlabeled-learning-using-random","title":"Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization","date":"2022-10-16","arxiv_id":"2210.08461","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/label-free-explainability-for-unsupervised","title":"Label-Free Explainability for Unsupervised Models","date":"2022-03-03","arxiv_id":"2203.01928","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/feature-importance-aware-transferable","title":"Feature Importance-aware Transferable Adversarial Attacks","date":"2021-07-29","arxiv_id":"2107.14185","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/collection-and-validation-of","title":"Collection and Validation of Psychophysiological Data from Professional and Amateur Players: a Multimodal eSports Dataset","date":"2020-11-02","arxiv_id":"2011.00958","repositories_listed":3,"syntology":null},{"url":"/paper/relative-feature-importance","title":"Relative Feature Importance","date":"2020-07-16","arxiv_id":"2007.08283","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-nonparametric-statistical-inference","title":"Efficient nonparametric statistical inference on population feature importance using Shapley values","date":"2020-06-16","arxiv_id":"2006.09481","repositories_listed":3,"syntology":{"n":25,"n_ran":15,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/a-debiased-mdi-feature-importance-measure-for","title":"A Debiased MDI Feature Importance Measure for Random Forests","date":"2019-06-26","arxiv_id":"1906.10845","repositories_listed":3,"syntology":null},{"url":"/paper/evaluating-feature-importance-estimates","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","date":"2018-06-28","arxiv_id":"1806.10758","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/distributed-and-parallel-time-series-feature","title":"Distributed and parallel time series feature extraction for industrial big data applications","date":"2016-10-25","arxiv_id":"1610.07717","repositories_listed":3,"syntology":null},{"url":"/paper/feature-responsiveness-scores-model-agnostic","title":"Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse","date":"2024-10-29","arxiv_id":"2410.22598","repositories_listed":2,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/an-unsupervised-approach-to-achieve","title":"An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records","date":"2024-06-13","arxiv_id":"2406.08958","repositories_listed":2,"syntology":null},{"url":"/paper/provably-stable-feature-rankings-with-shap","title":"Statistical Significance of Feature Importance Rankings","date":"2024-01-28","arxiv_id":"2401.15800","repositories_listed":2,"syntology":null},{"url":"/paper/exiffi-and-eif-interpretability-and-enhanced","title":"Enhancing Interpretability and Generalizability in Extended Isolation Forests","date":"2023-10-09","arxiv_id":"2310.05468","repositories_listed":2,"syntology":null},{"url":"/paper/mdi-a-flexible-random-forest-based-feature","title":"Integrating Random Forests and Generalized Linear Models for Improved Accuracy and Interpretability","date":"2023-07-04","arxiv_id":"2307.01932","repositories_listed":2,"syntology":null},{"url":"/paper/measuring-implicit-bias-using-shap-feature","title":"Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps","date":"2023-05-16","arxiv_id":"2305.09399","repositories_listed":2,"syntology":null},{"url":"/paper/inseq-an-interpretability-toolkit-for","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","date":"2023-02-27","arxiv_id":"2302.13942","repositories_listed":2,"syntology":null},{"url":"/paper/openfe-automated-feature-generation-beyond","title":"OpenFE: Automated Feature Generation with Expert-level Performance","date":"2022-11-22","arxiv_id":"2211.12507","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/concept-activation-regions-a-generalized","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","date":"2022-09-22","arxiv_id":"2209.11222","repositories_listed":2,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/unifying-local-and-global-model-explanations","title":"Unifying local and global model explanations by functional decomposition of low dimensional structures","date":"2022-08-12","arxiv_id":"2208.06151","repositories_listed":2,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}