Feature Importance

Benchmarks archive 2025-07-28

6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 335 papers with code (890 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction
  23 May 2019 31 repositories listed Syntology ran 2 of 26 samples · 24 unverified · 3 pointer-only (licence)
  In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions.
• A Unified Approach to Interpreting Model Predictions
  22 May 2017 17 repositories listed Syntology ran 3 of 8 samples · 5 unverified · 6 pointer-only (licence)
  Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications.
• RISE: Randomized Input Sampling for Explanation of Black-box Models
  19 Jun 2018 13 repositories listed Syntology ran 1 of 34 samples · 33 unverified · 10 pointer-only (licence)
  We compare our approach to state-of-the-art importance extraction methods using both an automatic deletion/insertion metric and a pointing metric based on human-annotated object segments.
• FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine
  15 May 2019 12 repositories listed
  Although some CTR model such as Attentional Factorization Machine (AFM) has been proposed to model the weight of second order interaction features, we posit the evaluation of feature importance before explicit feature…
• Attention is not Explanation
  26 Feb 2019 9 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Attention mechanisms have seen wide adoption in neural NLP models.
• Interpretable machine learning: definitions, methods, and applications
  14 Jan 2019 6 repositories listed Syntology ran 2 of 27 samples · 25 unverified
  Official code for using / reproducing ACD (ICLR 2019) from the paper "Hierarchical interpretations for neural network predictions" https://arxiv.
• Understanding Global Feature Contributions With Additive Importance Measures
  1 Apr 2020 4 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability.
• Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees
  18 May 2019 4 repositories listed Syntology ran 4 of 6 samples · 2 unverified
  Tree ensembles, such as random forests and AdaBoost, are ubiquitous machine learning models known for achieving strong predictive performance across a wide variety of domains.
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
  10 Oct 2018 4 repositories listed
  The wide implementation of electronic health record (EHR) systems facilitates the collection of large-scale health data from real clinical settings.
• Nonparametric IPSS: Fast, flexible feature selection with false discovery control
  3 Oct 2024 3 repositories listed
  Extensive nonlinear simulations with RNA sequencing data show that both methods accurately control the false discovery rate and detect more true positives than existing methods.
• Interpretable machine learning for time-to-event prediction in medicine and healthcare
  17 Mar 2023 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Time-to-event prediction, e.
• Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization
  16 Oct 2022 3 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 2 pointer-only (licence)
  Key to our approach is a new interpretation of decision tree algorithms for positive and negative data as \emph{recursive greedy risk minimization algorithms}.
• Label-Free Explainability for Unsupervised Models
  3 Mar 2022 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Unsupervised black-box models are challenging to interpret.
• Feature Importance-aware Transferable Adversarial Attacks
  29 Jul 2021 3 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 1 pointer-only (licence)
  More specifically, we obtain feature importance by introducing the aggregate gradient, which averages the gradients with respect to feature maps of the source model, computed on a batch of random transforms of the…
• Collection and Validation of Psychophysiological Data from Professional and Amateur Players: a Multimodal eSports Dataset
  2 Nov 2020 3 repositories listed
  An important feature of the dataset is simultaneous data collection from five players, which facilitates the analysis of sensor data on a team level.
• Relative Feature Importance
  16 Jul 2020 3 repositories listed
  Interpretable Machine Learning (IML) methods are used to gain insight into the relevance of a feature of interest for the performance of a model.
• Efficient nonparametric statistical inference on population feature importance using Shapley values
  16 Jun 2020 3 repositories listed Syntology ran 15 of 25 samples · 10 unverified
  The true population-level importance of a variable in a prediction task provides useful knowledge about the underlying data-generating mechanism and can help in deciding which measurements to collect in subsequent…
• A Debiased MDI Feature Importance Measure for Random Forests
  26 Jun 2019 3 repositories listed
  Based on the original definition of MDI by Breiman et al.
• A Benchmark for Interpretability Methods in Deep Neural Networks
  28 Jun 2018 3 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks.
• Distributed and parallel time series feature extraction for industrial big data applications
  25 Oct 2016 3 repositories listed
  This problem is especially hard to solve for time series classification and regression in industrial applications such as predictive maintenance or production line optimization, for which each label or regression target…
• Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse
  29 Oct 2024 2 repositories listed Syntology ran 0 of 7 samples · 7 unverified
  We propose to address these issues by highlighting features based on their responsiveness score -- i.
• An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records
  13 Jun 2024 2 repositories listed
  Electronic healthcare records are vital for patient safety as they document conditions, plans, and procedures in both free text and medical codes.
• Statistical Significance of Feature Importance Rankings
  28 Jan 2024 2 repositories listed
  Feature importance scores are ubiquitous tools for understanding the predictions of machine learning models.
• Enhancing Interpretability and Generalizability in Extended Isolation Forests
  9 Oct 2023 2 repositories listed
  This paper introduces Extended Isolation Forest Feature Importance (ExIFFI), a method that explains predictions made by Extended Isolation Forest (EIF) models, which split data using hyperplanes.
• Integrating Random Forests and Generalized Linear Models for Improved Accuracy and Interpretability
  4 Jul 2023 2 repositories listed
  Random forests (RFs) are among the most popular supervised learning algorithms due to their nonlinear flexibility and ease-of-use.
• Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps
  16 May 2023 2 repositories listed
  In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification.
• Inseq: An Interpretability Toolkit for Sequence Generation Models
  27 Feb 2023 2 repositories listed
  Past work in natural language processing interpretability focused mainly on popular classification tasks while largely overlooking generation settings, partly due to a lack of dedicated tools.
• OpenFE: Automated Feature Generation with Expert-level Performance
  22 Nov 2022 2 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  In the two competitions, features generated by OpenFE with a simple baseline model can beat 99.
• Concept Activation Regions: A Generalized Framework For Concept-Based Explanations
  22 Sep 2022 2 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  We further demonstrate empirically that CARs offer (1) more accurate descriptions of how concepts are scattered in the DNN's latent space; (2) global explanations that are closer to human concept annotations and (3)…
• Unifying local and global model explanations by functional decomposition of low dimensional structures
  12 Aug 2022 2 repositories listed
  The interventional SHAP value of feature k is a weighted sum of the main component and all interaction components that include k, with the weights given by the reciprocal of the component's dimension.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.