KL-LIME explains Bayesian models by projecting them locally to simpler models.
problem Explaining predictions of complex Bayesian models.
method Combines LIME with Bayesian projection methods.
result Demonstrates improved explanation of MNIST classifications.
WISCA generates consensus explanations from conflicting model-agnostic interpretability methods.
problem Conflicting explanations from diverse interpretability algorithms.
method WISCA integrates class probability and normalized attributions to generate consistent explanations.
result WISCA consistently aligns with the most reliable individual method, improving explanation reliability.
Programs as explanations for complex models without sacrificing accuracy.
problem Finding interpretable explanations for complex machine learning models without sacrificing accuracy.
method Prototype program induction method based on simulated annealing.
result Small programs can be expressive and intuitive as explanations for black-box classifiers.
ARFs generate plausible counterfactuals for models, improving model understanding.
problem Creating realistic counterfactuals for model analysis.
method Adversarial Random Forests (ARFs) for generating plausible counterfactuals.
result ARFs efficiently generate plausible counterfactuals in a model-agnostic way.
Proposes a framework for creating custom surrogate explanations.
problem Misunderstanding of LIME as the solution for surrogate explanations.
method Decomposes surrogate explainers into algorithmically independent modules.
result Empowers researchers to create custom local surrogate explanations.
Paper introduces algorithms for explaining monotonic classifiers.
problem Need for explanations of monotonic classifiers.
method Polynomial algorithms for formal explanations of monotonic classifiers.
result Efficient model-agnostic algorithm for enumerating explanations.
Proposes a method for explaining ranking decisions in learning systems.
problem Limited work on interpreting ranking decisions from learning systems.
method Model agnostic local explanation method using optimization to maximize validity.
result Approach outperforms other methods in validity across different LTR models.
IRDs provide local, model-agnostic explanations using hyperboxes.
problem Local model-agnostic explanations for machine learning predictions.
method Formalizes IRDs as hyperboxes, defines optimization problem, introduces unified framework.
result IRDs offer semi-factual explanations and highlight feature importance.
aLIME produces clear rule-based explanations for model predictions.
problem Interpreting machine learning models for accurate human predictions.
method Anchor-LIME (aLIME) for model-agnostic rule-based explanations.
result aLIME produces high-precision rule-based explanations with clear coverage boundaries.
A new method improves LIME for better model explanation.
problem Current LIME explanations are not faithful and weak in understanding.
method Proposes a novel Modified Perturbed Sampling (MPS) for LIME.
result MPS-LIME achieves better performance in understandability, fidelity, and efficiency.
This paper advocates for explaining machine learning predictions using model-agnostic methods.
problem The need for interpretability in machine learning models.
method Model-agnostic approaches that treat models as black-box functions.
result Model-agnostic approaches provide flexibility in explanations and representations.
Mahé provides hierarchical explanations for complex interactions in machine learning models.
problem Capturing and explaining complex interactions in machine learning models.
method Model-agnostic hierarchical explanations through local interpretation and context-free generalization.
result Improved local interaction interpretations and successful explanation of context-free interactions.
Local surrogate explainers vary in objectives, leading to incomparable explanations.
problem Variability in objectives among local surrogate explainers.
method Review of multiple local surrogate explainers, focusing on extracted information.
result Diverse explanations from similar methods due to differing objectives.
Proposes a deterministic LIME for CAD systems.
problem Instability in LIME explanations.
method Uses agglomerative HC and KNN to select relevant clusters and trains a linear model.
result DLIME is more stable than LIME.
New algorithm generates counterfactual explanations for diverse models without restrictions.
problem Supporting consequential decisions with understandable explanations for predictive models.
method Solves satisfiability problems using logic formulae for model-agnostic, diverse explanations.
result Generates diverse, plausible counterfactuals at provably optimal distances.
Proposes MOC method for better counterfactual explanations in ML models.
problem Difficulties in balancing multiple objectives for counterfactual explanations.
method Translates counterfactual search into a multi-objective optimization problem.
result Returns diverse counterfactuals with different trade-offs and maintains feature diversity.
A new method for generating counterfactual explanations in high-dimensional datasets.
problem Creating realistic counterfactual explanations in complex, high-dimensional data.
method A discretized approach using binary search and boundary approximation.
result Our method reduces the distance between counterfactuals by 5% to 50% in terms of the L2 norm.
CLE explains any classifier predictions in plain terms.
problem Understanding complex classifier predictions.
method Model-agnostic explanation technique approximating locally using interpretable models.
result CLE provides faithful and interpretable explanations for various classifiers.
MACEM generates contrastive explanations for any classification model.
problem Generating meaningful explanations for non-differentiable models.
method Model Agnostic Contrastive Explanations Method (MACEM) for any classification model.
result MACEM generates contrastive explanations for models like random forests and boosted trees.
SurvSHAP(t) explains time-dependent survival predictions from machine learning models.
problem Interpreting complex survival models for time-dependent effects.
method SHapley Additive exPlanations (SHAP) adapted for time-dependent survival predictions.
result SurvSHAP(t) detects time-dependent effects and improves variable importance detection.
New method interprets complex models by altering images.
problem Need to explain complex machine learning predictions.
method General framework for model-agnostic explanations.
result Find most responsible part of an image for a classifier.
Proposes a method to generate counterfactual and contrastive explanations using SHAP.
problem Need for explainable AI and legal requirement for model interpretability.
method Model agnostic method using SHAP to generate contrastive and counterfactual explanations.
result Demonstrates effectiveness of the method on various datasets.
The paper investigates the limitations of additive explanations for complex models.
problem The trustworthiness of additive explanations for non-additive models.
method Examine and introduce a new method to detect interactions for instance-level explanations.
result Additive explanations can be misleading for non-additive models.
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.
ExpO regularizes models to improve their explainability.
problem Improving the interpretability of black-box models.
method ExpO is a hybridization of regularization and post-hoc explanation systems.
result Post-hoc explanations for ExpO-regularized models have better explanation quality.
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.
The abstract discusses various machine learning explanation methods.
problem Improving the understanding and trust in machine learning models.
method Exploratory methods for assessing machine learning models.
result Various methods exist, each with its own strengths and applications.
ASVs incorporate causal knowledge into AI explainability.
problem AI explainability and fairness in models.
method Introduces Asymmetric Shapley values (ASVs) to incorporate causal structure.
result ASVs improve model explanations, detect unfair discrimination, and support feature selection.
A deep RL approach generates counterfactual instances efficiently.
problem Efficient generation of counterfactual instances for large datasets and diverse models.
method Deep reinforcement learning to optimize counterfactual instances in a single forward pass.
result Model-agnostic and scalable counterfactual generation.
A fast method finds interpretable counterfactual explanations using class prototypes.
problem Finding understandable counterfactual explanations for classifier predictions.
method Using class prototypes, the method speeds up and improves interpretability of counterfactual instances.
result The method significantly speeds up and improves the interpretability of counterfactual explanations.
Two R packages explain complex model predictions by attributing them to input features.
problem Understanding complex model predictions from black box models.
method Introducing two new approaches: live and breakDown packages.
result Comparison of results with lime and ShapleyR.
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.
GANchors generates realistic image perturbations for better classifier explanations.
problem Improving the trustworthiness of image classification explanations.
method Using GANs to optimize a lower-dimensional latent space for realistic perturbation distributions.
result Generated images are more likely to be from the original training set, leading to more precise explanations.
RelEx explains relational models without gradient access.
problem Lack of explainability for relational models like GNNs and SRL.
method Model-agnostic explainer for relational models using only outputs.
result Comparable or better performance compared to GNN-Explainer.
Evaluates explanations of LTR models using decision paths and compares their accuracy.
problem Challenges in evaluating local explanations of LTR models due to lack of ground truth feature importance scores.
method Focuses on tree-based LTR models, extracts ground truth feature importance scores using decision paths, and compares them with explanation techniques.
result Explanation accuracy varies depending on the model and data point.
MAPLE provides faithful local explanations without sacrificing accuracy.
problem Designing effective interpretability systems that capture multiple explanation types.
method Local linear modeling with dual interpretation of random forests.
result MAPLE produces more faithful local explanations than LIME and is as accurate as random forests.
LIME explanations can be uncertain, even for accurate models.
problem Uncertainty in LIME explanations undermines trust in machine learning models.
method Demonstrated two sources of uncertainty in LIME: sampling randomness and varying interpretation quality.
result Uncertainty in LIME explanations is present even in high-performing models.
Identifies minimal feature subsets for black-box model decisions.
problem Local explanation techniques are limited and sensitive to irrelevant features.
method Sufficient input subsets for same decision with minimal features.
result Reveals global decision-making principles from feature patterns.
ManifoldShap improves model explanations by restricting evaluations to the data manifold.
problem Inaccurate and misleading model explanations due to reliance on out-of-distribution data.
method Restricts model evaluations to the data manifold to avoid off-manifold perturbations.
result ManifoldShap provides more accurate and intuitive explanations than existing methods.
Paper introduces Native Guide for generating time series counterfactual explanations.
problem Lack of explainability for time series data in AI systems.
method Model-agnostic, instance-based counterfactual generation for time series classification.
result Native Guide produces better counterfactual explanations than benchmarks.
Concepts simplify complex models for better understanding.
problem Difficulty in generating understandable explanations for high-dimensional tabular datasets with correlated variables.
method Introduces concepts as groupings of correlated variables and embeds them in a surrogate decision tree.
result Improvement in human interpretability of surrogates without sacrificing accuracy and fidelity.
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 method provides calibrated feature importance explanations for regression models.
problem Lack of uncertainty quantification in existing local explanation methods.
method Extension of Calibrated Explanations method to support regression and probabilistic regression.
result Calibrated Explanations for regression provides quantified uncertainty and robust explanations.
Method finds counterfactual explanations for random forest models.
problem Limited interpretability of random forest models in regulated industries.
method Similarity learning exploiting random forest's feature representation.
result Generated explanations are sparser and more useful than Shapley values.
Researchers show how to manipulate Partial Dependence plots to deceive explanations of predictive models.
problem The robustness and trustworthiness of Partial Dependence (PD) explanations are compromised.
method Data poisoning using genetic and gradient algorithms to manipulate PD plots.
result PD explanations can be fooled and manipulated to mislead understanding of predictive models.
TaylorPODA uses Taylor expansions to improve feature attributions for opaque models.
problem Lack of systematic framework for quantifying feature contributions in opaque models.
method Taylor expansion framework with postulates (precision, federation, zero-discrepancy, adaptation).
result TaylorPODA achieves competitive results and provides principled explanations.
LIMEtree offers faithful explanations for multiple classes in predictive models.
problem Generating explanations for several classes can be difficult due to conflicting evidence.
method LIMEtree uses multi-output regression trees for consistent and faithful explanations of multiple classes.
result LIMEtree provides diverse explanation types and outperforms LIME in evaluations.
GLIME improves LIME's stability and local fidelity.
problem LIME's instability and low local fidelity.
method Introducing GLIME, an enhanced framework that derives an equivalent formulation of LIME with faster convergence and improved stability.
result GLIME generates explanations with higher local fidelity and is independent of reference choice.