CTE improves explanation estimation with less data and faster computation.
problem Inefficient and inaccurate explanation estimation in machine learning models.
method Distribution compression through kernel thinning to reduce sample size.
result CTE significantly improves accuracy and stability of explanation estimation.
δ-CLUE generates diverse explanations for model uncertainty.
problem Lack of constraints in generating explanations for uncertainty estimates.
method Augmenting CLUE approach to provide a set of plausible explanations.
result Returns a set of diverse inputs that yield confident predictions.
The study evaluates how well local explanations align with model predictions.
problem Capturing the faithfulness of local explanations to model predictions.
method Introducing consistency and sufficiency as properties, and developing quantitative measures and estimators.
result Quantitative measures of consistency and sufficiency depend on test-time data distribution.
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
SurvBeX explains ML survival models using Beran estimator.
problem Interpreting predictions of machine learning survival models.
method Uses modified Beran estimator as surrogate model to compute feature impacts.
result SurvBeX minimizes mean distance between black-box and surrogate model survival functions.
This work defines observation-specific explanations for black-box models.
problem Assigning importance to data points in black-box model predictions.
method Surrogate model construction using scattered data approximation and orthogonal matching pursuit.
result Validated approach on simulated and real-world datasets.
New method for explaining dialogue response generation models.
problem Interpreting sequence generation models, especially dialogue response generation.
method Local Explanation of Response Generation (LERG) method.
result LERG improves dialogue response generation explanations compared to existing methods.
New methods improve uncertainty explanations for models.
problem Improving interpretation of uncertainty estimates from probabilistic models.
method Developed new methods to generate diverse and global explanations for uncertain model predictions.
result Generated diverse and global explanations for uncertain model predictions, addressing previous limitations.
The increasing deployment of machine learning as well as legal regulations such as EU's GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models. Counterfactual explanations are considered as one of the most popular techniques to explain a specific decision of a model. While the…
ACE improves counterfactual explanations with fewer model queries.
problem Inefficient sampling for counterfactual explanations in machine learning models.
method Adaptive sampling combining Bayesian estimation and stochastic optimization.
result ACE achieves superior evaluation efficiency compared to state-of-the-art methods.
DTOR explains anomalies with rule-based explanations.
problem Need to explain anomalies in data effectively.
method Applies Decision Tree Regressor to estimate anomaly scores and generate rule-based explanations.
result DTOR produces robust and consistent rule-based explanations.
The paper introduces a method to assess the reliability of model explanations.
problem Assessing the quality and reliability of model explanations.
method An Ordinal Consensus Approach using diverse bootstrapped surrogate explainers.
result Uncertainty estimates offer actionable insights beyond standard surrogate explainers.
Paper proposes Coalitional BAE to improve explainability of unsupervised deep learning models.
problem Improving explainability of Autoencoder's predictions.
method Introduces Coalitional BAE, inspired by agent-based system theory, to reduce correlation in explanations.
result Improved quality of explanations using Coalitional BAE on publicly available datasets.
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…
CLUE method interprets uncertainty from BNNs by showing how inputs change to increase confidence.
problem Lack of work on interpreting uncertainty estimates from probabilistic models.
method CLUE method uses counterfactual explanations to interpret uncertainty from BNNs.
result CLUE outperforms baselines and helps practitioners understand predictive uncertainty.
Measures faithfulness of LLM explanations to reveal hidden biases and misleading claims.
problem LLM explanations can misrepresent the model's reasoning process, leading to over-trust and misuse.
method Defines faithfulness in terms of concept influence and uses counterfactuals and Bayesian models to estimate it.
result Can quantify and discover interpretable patterns of unfaithfulness in LLM explanations.
The paper develops statistical inference methods for SHAP values.
problem Lack of statistical inference for SHAP values in model-agnostic feature importance.
method Semi-parametric approach using U-statistics and Neyman orthogonal scores for functionals of nested regressions.
result Asymptotically normal estimates of the pth powers of SHAP values for various p.
Much work aims to explain a model's prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estimates given an input at each time step. When the estimated risk increases, the goal of the explanation is to attribute the increase to a few r…
Bayesian framework improves reliability and consistency of model explanations.
problem Inconsistent and unreliable explanations from state-of-the-art methods.
method Developed a novel Bayesian framework for generating local explanations with associated uncertainty.
result Generated explanations are consistent, stable, and provide credible intervals for feature importances.
FastSHAP speeds up Shapley value estimation for black-box models.
problem Efficiently calculating Shapley values for complex models.
method Uses a learned explainer model in a single forward pass.
result Generates high-quality explanations with significant speedup.
This paper improves DNN generalization by accurately estimating mutual information.
problem Intractability of estimating mutual information in DNNs.
method Introduces a probabilistic representation of DNNs to accurately estimate mutual information.
result Derives a tighter generalization bound than previous relaxations.
Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2X) are of great use in data-heavy industries for model diagnostics, and for end-user explanations. These methods generally return either a weighting or subset of input features as an explanation of the classification of an instance. An alternative …
Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent th…
We provide a unified view of additive explanations for dependent inputs.
problem Challenges in obtaining a tractable representation and estimating the decomposition for dependent inputs.
method Combining Hilbert space methods with generalized functional ANOVA, we build an explicit decomposition Riesz Basis.
result Proposed a simple yet powerful algorithm to estimate the decomposition from data.
Improved Shapley Values for tree-based models, more accurate than existing methods.
problem Inaccurate Shapley Values in tree-based models leading to poor explanations.
method Introduced two new estimators exploiting tree structure, derived correct approach for categorical variables.
result More accurate Shapley Values for tree-based models, demonstrated through simulations.
P-SE explains model decisions with minimal feature subsets and fast estimators.
problem Explain model decisions in regression and classification.
method Probabilistic Sufficient Explanations (P-SE) with random Forests for conditional probability estimation.
result Consistent and efficient explanations for regression and classification models.
DDSME outperforms SME in estimating multimodal distributions.
problem Efficiency of score matching in multimodal distributions.
method Diffusion-based denoising score matching (DDSME) compared to vanilla score matching (SME).
result DDSME avoids the error bound deterioration of SME with increasing mode separation.
New insights on Shapley value precision for tabular data predictions.
problem Precision of Shapley value explanations for individual observations.
method Conditional Shapley value estimation methods for tabular data.
result Shapley value explanations are less precise for outer observations.
New methods for estimating conditional Shapley values compared and evaluated.
problem Estimating precise conditional Shapley values for tabular data models.
method Developed new and extended methods using Monte Carlo integration and regression.
result Recommendations for choosing between Monte Carlo and regression methods based on data distribution.
The paper uses statistics to improve the explainability of models.
problem Subjective human assessment of explanations and lack of theoretical guarantees.
method Leveraging statistical estimators for proper definition and evaluation of explanations.
result Statistical tools provide theoretical guarantees and evaluation metrics for explanations.
EAGLE improves reproducibility and stability of model explanations.
problem Creating reliable explanations for opaque machine learning models.
method Formulates perturbation selection as an information-theoretic active learning problem.
result EAGLE learns a linear surrogate model with feature importance scores and uncertainty estimates.
MCCE generates realistic counterfactual explanations for tabular data.
problem Creating valid and actionable counterfactual explanations for complex tabular data.
method MCCE models the joint distribution of features and decision using an autoregressive generative model with decision trees. It samples counterfactuals and removes invalid ones.
result MCCE outperforms state-of-the-art methods on various performance metrics and is faster.
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
Proposes a simple method to explain aleatoric uncertainty in neural networks.
problem Lack of transparent explanations for uncertainty estimates in AI models.
method Adapting a neural network with Gaussian output to estimate predictive variance and applying explainers to the variance output.
result The proposed method explains uncertainty more reliably than complex approaches and outperforms them in most settings.
Proposes GPR with local explanation for feature interpretation.
problem Lack of feature interpretation in Gaussian process regression.
method Introduces a locally linear model to explain feature contributions in GPR predictions.
result Achieves comparable predictive performance to GPR and superior interpretability.
This paper analyzes errors in Shapley value-based model explanations.
problem Biased or unreliable explanations from existing SVA methods.
method Error theoretical analysis framework decomposing errors into observation and structural biases.
result Trade-off between observation and structural biases in SVA explanations.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
Paper introduces CoD for few-shot task-aware knowledge distillation using counterfactual explanations.
problem Lack of data for task-aware distillation in resource-constrained scenarios.
method Counterfactual-explanation-infused Distillation CoD for few-shot task-aware knowledge distillation.
result CoD achieves superior performance with significantly fewer samples than baseline methods.
New experiments show deep networks benefit from memorizing rare data points.
problem Understanding why neural networks perform well on training data.
method Estimating influence and memorization values of training examples.
result Deep networks benefit from memorizing rare data points for good performance.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while…
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimations of errors and uncertainties are crucial. To address this issue we propose a Bayesian framework th…
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
SurvFD and SurvSHAP-IQ provide interpretable survival models by analyzing feature interactions.
problem Non-additivity of hazard and survival functions limits standard additive explanation methods.
method SurvFD decomposes higher-order effects into time-dependent and time-independent components, extending Shapley interactions to time-indexed functions.
result SurvFD and SurvSHAP-IQ offer a new perspective on survival explanations, explicitly characterizing feature interactions.
G-SHAP generates multiple types of explanations for machine learning models.
problem Understanding model predictions and their differences across groups.
method Generalization of SHAP method to produce additional types of explanations.
result G-SHAP produces explanations for classification, intergroup differences, and model failure.