DFI maps covariates to latent representations for feature importance.
problem Feature importance when predictors are statistically dependent.
method Disentangled Feature Importance (DFI) using entropic optimal transport.
result DFI yields stable, interpretable, uncertainty-quantified attributions of shared predictive signal.
Introduces RFI for assessing feature importance relative to any subset of features.
problem Lack of nuanced feature importance computation.
method Generalizes PFI and CFI to assess relative feature importance.
result Derives general interpretation rules for RFI.
Combining feature importance estimates improves reliability of machine learning predictions.
problem Lack of consensus on feature importance quantification makes explanations unreliable.
method Proposes a feature importance fusion framework combining multiple quantifiers.
result Feature importance ensembles reduce prediction error by 15%.
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance…
This paper shows feature importance remains valid even in low-performing models.
problem Feature importance validity in low-performing machine learning models for biomedical data.
method Experiments with synthetic and real biomedical datasets to compare feature rank stability under different data reductions.
result Feature importance can be maintained even at low performance levels if data size is adequate.
New methods reduce extrapolation errors in feature importance.
problem Flawed feature importance methods using unrestricted permutations lead to extrapolation errors.
method Three new approaches: conditional model reliance, Knockoffs with Gaussian transformation, and restricted ALE plot designs.
result Theoretical and numerical results show our strategies reduce/eliminate extrapolation.
A new method for measuring conditional feature importance using generative models.
problem Challenges in evaluating feature importance given other feature values.
method Adversarial Random Forest (ARF) for generating on-manifold data points.
result cARFi method yields robust importance scores adaptable for various feature importance notions.
New method disentangles feature importance scores in machine learning.
problem Misinterpretation of feature importance scores due to interactions and dependencies.
method Derive DIP (Disentangled Importance) decomposition of feature importance scores.
result DIP decomposition uniquely separates standalone contributions from interactions and dependencies.
This study compares feature importance and explainability in quantum vs classical ML models.
problem Lack of transparency in ML models, especially in sensitive fields.
method Comparison of classical ML (SVM, Random Forest) and hybrid quantum ML (VQC, QSVC) models using feature importance and explainability methods.
result Quantum ML models provide insights similar to classical models but with unique quantum features.
A new imputation method considers feature importance for missing value completion.
problem Missing values in datasets reduce accuracy and increase processing difficulty.
method Iterative matrix completion with feature importance learning.
result The method outperforms existing imputation algorithms on various datasets.
Develops method to assess feature importance in black-box models for unconditional distribution.
problem Lack of methods to analyze feature importance in black-box models for unconditional distribution.
method Approximation method to compute feature importance curves for unconditional distribution.
result Produces sparse and faithful results, computationally efficient.
A framework infers feature importance with uncertainties for high-dimensional data.
problem Estimating feature importance in high-dimensional data with uncertainty.
method Shapley value based framework, sub-SAGE, bootstrapping.
result Uncertainties in feature importance can be estimated from bootstrapping.
UMFI improves feature importance methods by reducing runtime and enhancing performance.
problem Improving feature importance methods to better explain causal and associative relationships in data.
method Introducing UMFI, which uses dependence removal techniques from AI fairness literature.
result UMFI outperforms MCI, especially in complex data scenarios, and reduces runtime from exponential to super-linear.
CDAM improves attention maps for ViTs, making them more class-sensitive.
problem Existing attention maps in ViTs lack class sensitivity.
method Class-discriminative attention maps (CDAM) that scale attention scores by class relevance.
result CDAM provides more class-sensitive explanations than existing methods.
TRIP detects unreliable feature importance scores in random forests.
problem Unreliable feature importance scores in random forests due to model extrapolation.
method Develops TRIP (Test for Reliable Interpretation via Permutation) to detect unreliable permutation feature importance scores.
result TRIP reliably detects unreliable permutation feature importance scores in high-dimensional settings.
CatNet controls FDR in LSTM models using SHAP feature importance and Gaussian mirrors.
problem Controlling False Discovery Rate (FDR) in LSTM models with feature selection.
method CatNet uses SHAP values for feature importance and Gaussian Mirror algorithm for FDR control. It introduces a kernel-based independence measure to handle feature correlations.
result CatNet reduces overfitting and improves model interpretability on simulated and real-world data.
A framework for quantifying uncertainty in feature importance values.
problem Stable interpretation of feature importance values in machine learning models.
method A novel method based on pairwise comparisons of feature importance values to produce confidence intervals for feature ranks.
result The method produces simultaneous confidence intervals for feature ranks, enabling selection of top-k important features.
This review explores XAI in finance, highlighting common techniques and areas needing improvement.
problem Balancing accuracy and transparency in financial AI models.
method Bibliometric and content analysis of XAI applications in finance.
result Post-hoc interpretability techniques are most used in financial XAI.
A novel validation method improves feature importance analysis in subject-specific ML models.
problem Limited effectiveness of general ML models trained on large datasets for individual patient outcomes.
method A novel validation approach using a general ML model with repeated trials and random seed variation.
result Consistent identification of key features at the subject level and improved group-level feature importance analysis.
One often finds in the literature connections between measures of fairness and measures of feature importance employed to interpret trained classifiers. However, there seems to be no study that compares fairness measures and feature importance measures. In this paper we propose ways to evaluate and compare such measure…
BIF assesses feature importance using Dirichlet distribution and Bayesian inference.
problem Quantitative feature importance assessment in statistical models.
method Utilizes Dirichlet distribution for probabilistic feature importance assessment via approximate Bayesian inference.
result Learned importance provides relative significance and confidence quantification of features.
Local MDI+ improves feature importance for tree-based models, enhancing interpretability and performance.
problem Lack of instance-specific feature importance for tree-based models.
method Local MDI+ extends MDI+ framework to provide instance-specific feature importances.
result Local MDI+ outperforms existing baselines, improving predictive performance by 10%.
We present an Automatic Relevance Determination prior Bayesian Neural Network(BNN-ARD) weight l2-norm measure as a feature importance statistic for the model-x knockoff filter. We show on both simulated data and the Norwegian wind farm dataset that the proposed feature importance statistic yields statistically signific…
TIME explains temporal models by analyzing feature importance.
problem Existing methods struggle with temporal models and feature importance.
method Model-agnostic permutation-based approach, temporal feature importance, hypothesis testing.
result TIME provides statistical rigor for explaining temporal models.
Have you ever wondered how your feature space is impacting the prediction of a specific sample in your dataset? In this paper, we introduce Single Sample Feature Importance (SSFI), which is an interpretable feature importance algorithm that allows for the identification of the most important features that contribute to…
High-dimensional spectroscopy data makes ML models achieve near-perfect accuracy, even when chemical distinctions are absent.
problem Why machine learning models achieve near-perfect accuracy in spectroscopic classification tasks without chemically meaningful features.
method Theoretical analysis grounded in the Feldman-Hajek theorem and concentration of measure, combined with specific experiments on synthetic and real fluorescence spectra.
result Infinitesimal distributional differences in high-dimensional spaces can lead to perfect separability, making models achieve near-perfect accuracy in spectroscopy.
RAMPART ranks top-k features more accurately than existing methods.
problem Accurate ranking of important features in machine learning.
method Adaptive sequential halving strategy combined with ensembling techniques.
result RAMPART achieves the correct top-k ranking with high probability.
Feature importance estimates that inform users about the degree to which given inputs influence the output of a predictive model are crucial for understanding, validating, and interpreting machine-learning models. However, providing fast and accurate estimates of feature importance for high-dimensional data, and quanti…
Paper proposes a new method for feature importance in model selection.
problem Feature importance in model selection.
method New tree-model explanation approach using Coefficient of Variation of feature weight.
result Novel feature explanation performs better than cross-validation in model selection.
Combines RFs and GLMs for better accuracy and interpretable feature importance.
problem Inability to interpret random forests (RFs) due to black box nature and unstable feature importance methods.
method Reinterprets decision trees and MDI as linear regression and R² values, combining RFs and GLMs in RF+.
result MDI+ outperforms existing feature importance measures in identifying signal features and stability.
Cluster LOCO: A model-agnostic feature importance score for interpreting cluster outputs
problem Interpreting and auditing cluster outputs
method Cluster LOCO (Leave-One-Covariate-Out)
result More reliably recovers informative features than existing methods
Two new methods assess feature importance for fairness in machine learning models.
problem Understanding how features influence fairness in machine learning models.
method Two model-agnostic approaches: permutation and occlusion.
result Simple, scalable, and interpretable methods to quantify feature importance for fairness.
Black-box neural network models are widely used in industry and science, yet are hard to understand and interpret. Recently, the attention mechanism was introduced, offering insights into the inner workings of neural language models. This paper explores the use of attention-based neural networks mechanism for estimatin…
A method to improve clustering explainability using bagging and feature dropout.
problem Lack of explainability in clustering methods.
method Bagging and feature dropout to generate feature importance scores.
result Improved stability and robustness of cluster definition, especially in small-sample or noisy settings.
New methods ensure feature importance rankings are correct with high probability.
problem Stability issues in feature importance scores due to random sampling.
method Hypothesis testing-based techniques to assess and verify the stability of top-ranked features.
result Ensures the most important features are correct with high-probability guarantees.
Develops fair feature importance scores for tree-based models to interpret fairness.
problem Ensuring fairness in machine learning models, especially tree-based ones.
method Inspired by decision trees, proposes a novel fair feature importance score based on mean decrease in group bias.
result Valid interpretations of fairness for tree-based ensembles and surrogates of other ML systems.
We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature importance that are not better than a random designation …
Proposes a new method for interpreting feature importance and effects in dependent feature models.
problem Challenges in interpreting feature importance when features are dependent and interactions are present.
method Conditional Subgroup Approach
result Conditional PFI and PDP estimates based on this approach often outperform existing methods.
A novel approach combines feature importance scores with deep learning for forex price prediction.
problem Improving forex price prediction using deep learning models.
method Feature importance recap combined with stacking models.
result Proper feature selection significantly improves model performance.
Introduces joint Shapley values to measure feature importance in models.
problem Measuring the importance of feature sets in machine learning models.
method Extends Shapley's axioms to measure a set of features' average contribution to a model's prediction.
result Joint Shapley values provide unique insights and are more consistent with local intuitions.
New method disentangles high-order effects in feature importance.
problem Quantifying cooperative effects in feature importance.
method Adaptive Leave One Covariate Out (LOCO) method to decompose LOCO into two-body and higher-order components.
result Decomposes LOCO into two-body and higher-order components, highlighting synergistic and redundant effects.
The paper introduces logic constraints to improve AI model interpretability.
problem The black box nature of AI models limits their trustworthiness in high-stakes fields.
method The paper extends AI models with logic constraints to make feature importance more interpretable.
result Promising experimental results have been achieved for the Adult dataset.
DEDACT breaks down feature importance into direct and associative components.
problem Lack of clear distinction between direct and associative feature importance.
method DEDACT framework to decompose direct and associative importance measures.
result Provides insight into sources of prediction-relevant information and feature pathways.
PRoFILE accurately estimates feature importance under distribution shifts.
problem Challenges in estimating feature importance under distribution shifts.
method PRoFILE uses a loss estimator trained with a causal objective to estimate feature importance.
result PRoFILE accurately estimates feature importance under complex distribution shifts.
Unified view of improving tree model interpretability and debiasing feature importance.
problem Improving interpretability and debiasing feature importance in tree-based models.
method Demonstrates a common thread among bias correction methods and local explanations for trees.
result Points out a bias in explainable AI for trees algorithms due to inbag data inclusion.
The paper reveals how clustering in ReLU networks enhances interpretability.
problem Improving interpretability of deep learning models.
method Clustering of ReLU neuron patterns to reveal underlying affine maps.
result The network's predictions can be explained by feature importance within clusters.
EBLIME enhances model explanations using Bayesian ridge regression.
problem Improving model explanations for black-box machine learning models.
method EBLIME uses Bayesian ridge regression to explain feature importance.
result EBLIME provides more intuitive and accurate feature importance rankings.
Complex problems may require sophisticated, non-linear learning methods such as kernel machines or deep neural networks to achieve state of the art prediction accuracies. However, high prediction accuracies are not the only objective to consider when solving problems using machine learning. Instead, particular scientif…