Interpretable companion model for black-box classifiers.
problem Dilemma between interpretable and black-box models.
method Trains a companion model from data and black-box model predictions, optimizing a combination of accuracy and complexity.
result Companion model provides interpretable predictions with a slight accuracy loss for user choice.
Interpretable machine learning has become a strong competitor for traditional black-box models. However, the possible loss of the predictive performance for gaining interpretability is often inevitable, putting practitioners in a dilemma of choosing between high accuracy (black-box models) and interpretability (interpr…
We interpret black box predictive models using causal attribution.
problem Interpreting models trained using machine learning in high-stakes applications.
method Estimate causal effects of model inputs on output using observational data.
result Effective interpretation of black box predictive models via causal attribution.
New method wraps black-box classifiers to reduce bias.
problem Reduction of bias in black-box predictions.
method Post-processing with α-trees and boosting algorithms.
result Demonstrated effectiveness in reducing bias across multiple fairness metrics.
Driven by an increasing need for model interpretability, interpretable models have become strong competitors for black-box models in many real applications. In this paper, we propose a novel type of model where interpretable models compete and collaborate with black-box models. We present the Model-Agnostic Linear Comp…
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.
tDB removes unfairness from black-box models using probability theory.
problem Mitigating unfairness in predictions from black-box models.
method towerDebias (tDB) method based on the Tower Property.
result tDB improves prediction fairness without retraining the original model.
Bayesian optimisation generates saliency maps for black-box models.
problem Generating saliency maps for models without access to parameters.
method Bayesian optimisation sampling method to find global salient regions.
result Approach outperforms grid-based methods and performs similarly to gradient-based methods.
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…
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.
Efficiently refits black box predictions with wild refitting method.
problem Computing high-probability upper bounds on prediction errors.
method Three-step procedure: residuals, symmetrization, and solving a modified prediction problem.
result Wild refitting provides an upper bound on prediction error with high probability.
We address challenges in collaborative black-box optimization through three frameworks.
problem Challenges in distributed experimentation, heterogeneity, and privacy in black-box optimization.
method Three unifying frameworks: global, local, and predictive.
result Shift from descriptive/predictive to prescriptive federated learning in black-box optimization.
This work addresses the situation where a black-box model with good predictive performance is chosen over its interpretable competitors, and we show interpretability is still achievable in this case. Our solution is to find an interpretable substitute on a subset of data where the black-box model is overkill or nearly …
Proposes a tabular transformer model to maintain feature effect intelligibility.
problem Losing marginal feature effects in deep tabular transformer networks.
method Adapts tabular transformer networks to identify marginal feature effects.
result The model accurately identifies marginal feature effects, matching black-box performance while maintaining intelligibility.
Proposes a method to explain black-box models using causal learning.
problem Existing explainability methods focus on micro-level inputs, not interpretable features.
method Learns causal graphical representations to differentiate between causal and confounding influences.
result Graphs can differentiate between interpretable and confounding features.
Paper proposes B3D method for black-box backdoor detection.
problem Detecting backdoor attacks in black-box models without access to training data.
method Gradient-free optimization to reverse-engineer triggers, simple strategy for reliable predictions.
result Effectiveness of B3D method corroborated on hundreds of DNN models.
The paper improves prediction intervals for non-parametric regression using histograms.
problem Computing accurate prediction intervals for non-parametric regression models.
method Uses conditional histograms to estimate conditional distributions and compute shortest prediction intervals.
result The method provides prediction intervals with provable marginal coverage and asymptotic conditional coverage.
Paper exposes vulnerabilities in interpreting machine learning models using adversarial attacks on PD plots.
problem Vulnerability of permutation-based interpretation methods, particularly PD plots, to adversarial attacks.
method Adversarial framework to manipulate black-box models and produce deceptive PD plots.
result It is possible to hide discriminatory behaviors in machine learning models through interpretation tools like PD plots.
Paper explores how black box models can deviate from average performance.
problem Understanding and interpreting predictions from sophisticated black box models.
method Two general approaches to provide interpretable descriptions of black box classification model performance.
result Identifies regions where black box models deviate significantly from their average performance.
Split conformal prediction provides finite-sample guarantees for black-box models without distributional assumptions.
problem Weak performance guarantees for modern predictive models under minimal assumptions.
method Develops finite-sample guarantees for split conformal prediction, a method that uses nested prediction sets and order statistics.
result The coverage of prediction sets based on order statistics stochastically dominates the Beta distribution.
Bayesian optimization enhanced with conformal prediction for better outcome reliability.
problem Uncertainty and model misspecification in Bayesian optimization.
method Conformal prediction to provide coverage guarantees and Bayesian optimization to select queries.
result Significant improvement in query coverage without sacrificing sample-efficiency.
RbX generates local explanations for black-box models using greedy polytope construction.
problem Generating interpretable local explanations for complex models.
method Greedy algorithm for building a convex polytope to approximate feature regions.
result RbX can more accurately identify important features compared to existing methods.
Interprets feature interactions in ad-click prediction models.
problem Improving interpretability of black-box recommender systems.
method Interprets feature interactions from a source model and encodes them in a target model.
result Interpretations significantly outperform existing recommender models.
SADA safely combines predictions from various models for semi-supervised learning.
problem Combining uncertain quality predictions from multiple models in semi-supervised learning.
method Safe and adaptive aggregation of black-box predictions.
result The method guarantees better performance than using labeled data alone and adapts to perfect predictions.
GONs improve predictions of maximizers from noisy black-box functions.
problem Estimating maximizers of noisy black-box functions.
method Global Optimization Networks (GONs) composed of invertible and unimodal functions.
result GONs outperform convex fits, GPR, and DNNs in prediction accuracy.
A new method for safer statistical inference after predictions.
problem Statistical inference with pseudo-outcomes from machine learning predictions.
method Prediction De-Correlated Inference (PDC) framework.
result PDC consistently outperforms supervised methods and can adapt to any model.
Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting…
Develops transparent global models consistent with local explanations.
problem Creating globally interpretable models that align with local explanations from black-box models.
method Custom boolean features from sparse local contrastive explanations are used to train a globally transparent model.
result Custom transparent models have higher local consistency compared to other strategies.
Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment.…
New bounds estimate learning algorithm performance using prediction information.
problem Estimating the performance of black-box learning algorithms.
method Information-theoretic bounds based on prediction information.
result Improved bounds applicable to deterministic algorithms and easier to estimate.
BAR reprograms black-box ML models for transfer learning with scarce data.
problem Transfer learning with limited data and resources.
method Zeroth-order optimization and multi-label mapping techniques to reprogram black-box models.
result BAR outperforms state-of-the-art methods and baseline transfer learning approaches.
Understanding black-box machine learning models is crucial for their widespread adoption. Learning globally interpretable models is one approach, but achieving high performance with them is challenging. An alternative approach is to explain individual predictions using locally interpretable models. For locally interpre…
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.
Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local su…
Adaptive uncertainty quantification improves black-box model predictions in generative AI.
problem Improving uncertainty quantification for black-box models in generative AI.
method Adaptive partitioning and local calibration of conformity scores.
result Local tightening of uncertainty sets with adaptive bands.
Wrapper improves black-box model auditability and decision trustworthiness.
problem Lack of transparency and auditability in machine learning models used in complex applications.
method Integrates uncertainty measures into black-box models to enhance auditability and decision trustworthiness.
result Improves trust in machine learning models by providing actionable mechanisms to reject uncertain predictions.
Proposes a method for explaining black-box models with nested feature attributions.
problem Making black-box models transparent and trustworthy.
method Model-agnostic local explanation method exploiting nested feature structure and consistency property.
result Accurate and consistent HiFAs and LoFAs estimated using fewer model queries.
BBCI uses meta prediction to estimate causal effects from datasets.
problem Estimating causal effects from observed data.
method Meta prediction to learn causal effect estimation.
result BBCI accurately estimates ATEs and CATEs across various causal inference problems.
Method makes non-interpretable models more intervenable.
problem Making non-interpretable models more understandable and controllable.
method Intervenability formalization and fine-tuning of black-box models.
result Fine-tuned black-box models are more intervenable and often better-calibrated.
Proposes a novel BO algorithm for stepwise model selection in sequence prediction.
problem Optimal model selection in sequential settings where model performance varies over time.
method Bayesian optimization with deep kernel learning to handle multiple black-box functions.
result Outperforms standard and multi-objective BO algorithms on sequence prediction tasks.
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.
Predictive modelling and supervised learning are central to modern data science. With predictions from an ever-expanding number of supervised black-box strategies - e.g., kernel methods, random forests, deep learning aka neural networks - being employed as a basis for decision making processes, it is crucial to underst…
Though black-box predictors are state-of-the-art for many complex tasks, they often fail to properly quantify predictive uncertainty and may provide inappropriate predictions for unfamiliar data. Instead, we can learn more reliable models by letting them either output a prediction set or abstain when the uncertainty is…
Proposes second-order influence functions for identifying influential groups in test-time predictions.
problem Identifying influential groups in test-time predictions for black-box models.
method Second-order approximations of the effect of removing a group of training samples on model predictions.
result Improves the correlation between computed influence values and ground truth values for linear models.
This paper proposes a novel PGO framework to optimize systemic risk bailouts using neural networks.
problem Optimal bailout strategies for mitigating systemic risk in financial systems.
method Prediction-Gradient-Optimization (PGO) framework, using neural networks to approximate and forecast the objective function.
result The PGO framework effectively manages systemic risk through online optimization.
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.
Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy load. Current predicti…
Proposes a new method to estimate variable importance in black box models, mitigating correlation effects.
problem Correlation between covariates affects the interpretation of variable importance parameters.
method Develops a modified LOCO (Leave Out COvariates) method and uses semiparametric models for estimation.
result Shows how to estimate a modified LOCO method that mitigates correlation effects.