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.
Hybrid model combines interpretable and black-box models for better transparency and performance.
problem Balancing interpretability and predictive performance in machine learning models.
method Proposes a Hybrid Predictive Model (HPM) integrating an interpretable model with a black-box model, using principled objective functions and customized training algorithms.
result Hybrid models achieve an efficient trade-off between transparency and predictive performance.
MALC combines interpretable linear models with black-box models for better predictions and transparency.
problem Combining interpretability with black-box models for better predictions.
method Formulates MALC as a convex optimization problem and uses accelerated proximal gradient method for training.
result MALC provides an efficient frontier balancing prediction accuracy and transparency.
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.
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.
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.
Efficiently distills white-box adversarial attacks into black-box models.
problem Generating efficient adversarial examples for robustness.
method Train a model to emulate white-box attack behavior and distill it into a more efficient black-box model.
result Reduces adversarial example generation time by 19x-39x and transfers to black-box settings.
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.
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.
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.
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 …
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…
Novel method interprets black box predictions using Fisher kernels and SBQ.
problem Interpreting black box models' predictions.
method Fisher kernels as feature embeddings, Sequential Bayesian Quadrature for selection.
result Method efficiently handles any subset of test predictions.
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.
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.
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.
REST improves robustness of black-box models to geometric transformations.
problem Overconfident incorrect predictions on out-of-distribution samples.
method REinforcement Spatial Transform learner (REST) that transforms input data into in-distribution samples.
result Improves robustness to geometric transformations and sample efficiency.
Interpretable semi-supervised classifier for black-box models with two self-labeling strategies.
problem Lack of labeled data and difficulty in explaining black-box models.
method Combines black-box and white-box approaches for self-labeling and prediction.
result Superior prediction rates and interpretability compared to state-of-the-art classifiers.
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.
Develops an axiomatic framework to assess quality of explanation methods for black box machine learning models.
problem Lack of interpretability in black box machine learning models.
method Proposes an axiomatic framework to compare and evaluate the quality of different explanation methods.
result The axiomatic framework is useful for assessing explanation quality and consistent with independent research.
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.
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.…
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 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.
LIMIS improves locally interpretable models by selecting and distilling key instances.
problem Low fidelity of locally interpretable models.
method LIMIS uses instance-wise subsampling guided by policy gradient and reward to improve fidelity.
result LIMIS near-matches black-box model accuracy while significantly improving fidelity.
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…
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.
Method uses elastic black-boxes to create interpretable models from complex ones.
problem Lack of trust and stability in opaque models and time-consuming feature engineering in interpretable models.
method Surrogate assisted feature extraction for model learning.
result Trains interpretable and accurate models without time-consuming feature engineering.
Black-box attacks on RL agents using temporal information.
problem Vulnerability of RL agents to adversarial samples.
method Sequence-to-sequence models for predicting future actions.
result Adversarial samples can trigger RL agents to misbehave after a delay.
Improves model classification accuracy in black-box settings.
problem Difficulty in inferring model properties due to limited query access.
method Introduces discriminative factorization to distinguish high-quality queries.
result Probability of chance-level classification decreases exponentially with query budget.
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.
Selective prediction-set models improve predictive reliability and uncertainty quantification.
problem Inaccurate and unreliable predictions from black-box models, especially for unfamiliar data.
method Training selective prediction-set models using uncertainty-aware loss minimization, and calculating well-calibrated prediction sets.
result Selective prediction-set models outperform existing approaches in predicting in-hospital mortality and length-of-stay for ICU patients.
Paper proposes hybrid approach for transparent credit scoring models.
problem Lack of transparency in machine learning models limits their use in regulated environments.
method Post-hoc interpretation of black-box models guides feature selection, followed by training glass-box models.
result Reduces feature usage from 106 to 10 while maintaining comparable performance.
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…
DiBO uses diffusion models to optimize high-dimensional black-box functions efficiently.
problem Optimizing high-dimensional and complex black-box functions efficiently.
method DiBO iterates two stages: training a diffusion model and casting candidate selection as posterior inference.
result DiBO outperforms state-of-the-art baselines across synthetic and real-world tasks.
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.
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.
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.
PRETZEL optimizes machine learning prediction serving systems for better performance.
problem Low latency, high throughput, and graceful performance degradation under heavy load in prediction serving systems.
method Introducing a novel white box architecture enabling both end-to-end and multi-model optimizations.
result Average 5.5x reduction in 99th percentile latency, 25x reduction in memory footprint, and 4.7x increase in throughput compared to state-of-the-art approaches.
Efficient black-box evasion attacks against deep networks with fewer queries.
problem Optimizing targeted evasion attacks with limited query budget.
method Formalized problem, evaluated benefits of using substitute models, presented two new attack strategies.
result Attack strategies are as effective as previous techniques but require significantly fewer queries.
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.
Extends batch active learning to non-differentiable models.
problem Efficiently training machine learning models on large, initially unlabelled datasets.
method Black-box batch active learning for regression tasks that relies solely on model predictions.
result Achieves strong performance on regression datasets compared to white-box approaches for deep learning 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.
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.
New method tests black box models for important features.
problem Control false discoveries in high-stakes model interpretations.
method Reframe interpretability as hypothesis testing, propose two testing methods.
result Tests control false discovery rate and select intuitive features.
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.