Quantifies interpretability and trust in ML decisions.
problem Measuring the quality and trustworthiness of ML interpretability methods.
method Proposes a quantitative measure based on information transfer rate and empirical validation.
result Empirical evidence shows the proposed metric differentiates interpretability methods and improves productivity.
TRUST improves tree models' accuracy while maintaining interpretability.
problem Piecewise-constant regression trees lack in predictive accuracy compared to black-box models.
method Combines Random Forest accuracy with interpretability of shallow trees and sparsity of linear models, using LLMs for explanations.
result TRUST outperforms other interpretable models in predictive accuracy and matches Random Forest's accuracy.
The paper explores AI in finance, focusing on XAI's role in enhancing interpretability and trust.
problem The need for AI in finance and the importance of XAI for better decision-making.
method Tracing AI's evolution in finance, highlighting XAI's role, and demonstrating through simulations.
result XAI enhances trust in AI systems, leading to more responsible decision-making.
TS-Insight visualizes Thompson Sampling for better debugging and trust.
problem Thompson Sampling's black box nature hinders debugging and trust.
method TS-Insight is a visual analytics tool that traces evolving posteriors and evidence counts.
result Visualizations help in verifying, diagnosing, and explaining Thompson Sampling dynamics.
New metrics help rebuild trust in Active Learning for industry practitioners.
problem Misalignment of objectives between research and industry in Active Learning.
method Presentation of actionable metrics to interpret AL strategies.
result Actionable metrics improve AL performance and interpretability.
New trust matrix quantifies breakdowns in deep neural networks.
problem Understanding trust breakdowns in deep learning models.
method Introduces trust matrix and conditional trust densities to analyze deep neural networks.
result Trust matrices reveal areas needing improvement for deep neural networks.
Paper explores using RL to teach ML models what is interpretable to non-technical users.
problem Lack of empirical evidence on what is interpretable to non-technical users.
method Train a neural network to provide risk assessments, then design a RL-based DSS to learn from user interactions.
result ML experts cannot accurately predict what will maximize user confidence in ML models.
Study finds machine learning interpretations are often unstable and unreliable.
problem Reliability of machine learning interpretations in high-stakes domains.
method Stability study on global interpretations using tabular data.
result Popular interpretation methods are frequently unstable, less stable than predictions, and not associated with prediction accuracy.
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also pr…
Optimizes explanations for linear models to enhance trust and interpretability.
problem Lack of well-defined interpretability for linear models and ad hoc approaches.
method Optimization framework using coordinate updates on coefficients.
result Derives a family of interpretability metrics for linear models.
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.
Automated feature engineering improves interpretable models without manual work.
problem Lack of interpretability in complex models causes trust and stability issues.
method Use elastic black-box models to create simpler, interpretable glass-box models.
result Extracted features from complex models improve linear model performance.
Framework enhances AI explainability by aligning with human cognitive models.
problem Lack of explainability in AI models hinders trust and accountability.
method Integrates explainability techniques with Malle's five category model of behavior explanation.
result Demonstrates practical relevance in credit risk assessment and regulatory analysis.
Study identifies key aspects of explainable ML for clinical trust.
problem Lack of concrete definitions for usable explanations in clinical settings.
method Surveyed clinicians from two specialties to understand their needs for explainability.
result Characterized specific aspects of explainability that improve trust in ML models.
In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given pathology image to be a malignant tumor, then the doctor may need to know which parts …
QUACKIE creates a new benchmark for NLP interpretability.
problem Evaluating NLP interpretability methods is challenging due to biased ground truths.
method Formulated a custom classification task from question-answering datasets, generating unbiased ground truths.
result Demonstrated the effectiveness of current interpretability methods on the new benchmark.
Explainable AI improves human decision accuracy but does not enhance it significantly.
problem Improving human decision-making through explainable AI.
method Comparing human decision accuracy with and without AI predictions, including or excluding explanations.
result Providing AI predictions improves human decision accuracy, but explanations do not significantly enhance it.
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.
Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and s…
Adaptive norms improve neural network optimization with second-order methods.
problem Optimizing neural networks with second-order methods.
method Regularized Newton methods with adaptive norms, interpreting adaptive gradient methods as trust region methods.
result Ellipsoidal constraints outperform spherical constraints in terms of backpropagations and asymptotic loss value.
Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this …
The paper defines a mathematical framework for measuring model interpretability.
problem Improving trust and understanding in machine learning models for complex decisions.
method Constructing interpretable steps in a sequence for various models, generalizing to a family of consistent measures.
result A formal definition of interpretability allows quantifying the tradeoff with predictive accuracy.
New metrics CWSA and CWSA+ improve model evaluation under confidence thresholds.
problem Lack of metrics capturing model reliability under confidence thresholds.
method Introducing CWSA and CWSA+ metrics that reward confident accuracy and penalize overconfident mistakes.
result CWSA and CWSA+ outperform classical metrics in trust-sensitive tests.
L-C2ST improves local diagnostics for SBI approximations.
problem Evaluating trustworthiness of posterior approximations in SBI.
method Local evaluation of posterior estimators at any observation.
result Offers better statistical power and interpretability.
Two multifidelity trust-region methods use low-fidelity models for efficient optimization.
problem Efficiently solving complex optimization problems with limited data.
method Sketched Trust-Region (STR) and SVD Trust-Region (SVDTR) methods using low-fidelity models.
result Potential gain in efficiency demonstrated through numerical examples.
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.
Trust-aware MAB improves learning performance by accounting for human deviation.
problem Learning performance suffers when humans deviate from recommended policies due to lack of trust.
method Integrates a dynamic trust model into MAB framework, establishing minimax regret and proposing a two-stage trust-aware procedure.
result Proves near-optimal statistical guarantees for trust-aware MAB algorithms.
Survey reviews explainability in AI for healthcare, emphasizing trust and transparency.
problem Lack of transparency hinders AI adoption in healthcare.
method Comprehensive literature review to guide explainable AI design.
result Quantitative evaluation metrics are needed for some explainability properties.
DeepCoDA provides personalized interpretability for complex health data.
problem Interpreting complex health data, especially compositional data, is challenging.
method DeepCoDA framework for high-dimensional compositional data, personalized interpretability through patient-specific weights.
result DeepCoDA maintains state-of-the-art performance and provides coherent, personalized interpretations.
Study finds transparency and model performance metrics increase trust in AutoML systems.
problem Understanding what information influences trust in AutoML systems.
method Three studies: qualitative interviews, controlled experiment, and card-sorting task.
result Transparency and model performance metrics are most important for establishing trust in AutoML systems.
Improves inference-time alignment for diffusion models without updating weights.
problem Aligning diffusion models without updating weights for high-reward outputs.
method Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC) for variance reduction and efficiency.
result Improves primary alignment objectives on text generation tasks.
New research finds tree-based GAMs are most trustworthy and fair.
problem Variability in GAM algorithms leads to inconsistent models.
method Quantitative and qualitative analysis of various GAM algorithms.
result Tree-based GAMs are the most trustworthy and fair.
AI system helps clinicians assess liver metastases quickly and with explanations.
problem Manual assessment of metastases is time-consuming and subjective.
method Interactive AI system with model interpretability.
result AI-assisted assessment improves efficiency and provides explanations.
New method interprets deep neural networks for better recommendation system understanding.
problem Making deep neural networks explainable for better user trust and understanding.
method Proposes a novel formulation of interpretable deep neural networks using masked weights and hidden features.
result Demonstrates models achieving close predictive performance with informative attributions.
New algorithm interprets clustering using optimal trees for healthcare applications.
problem Lack of interpretability in clustering algorithms limits their adoption in healthcare.
method Mixed Integer Optimization for Optimal Trees to generate interpretable partitions.
result Achieves comparable or superior performance with significantly higher interpretability.
Paper tackles interpretability in deep learning for multi-label learning.
problem Machine learning models are often hard to interpret.
method Combines deep autoencoder and multi-label classifiers.
result Proposes interpretable label hierarchies and dependencies.
causalKANs provides interpretable treatment effect estimates using neural networks.
problem The opacity of deep neural networks limits their adoption in sensitive domains.
method Proposes causalKANs, a framework that transforms neural estimators into interpretable closed-form formulas.
result causalKANs performs on par with neural baselines in CATE error metrics and offers a favorable accuracy--interpretability trade-off.
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.
DyS model improves survival analysis accuracy and interpretability.
problem Accurate and interpretable survival analysis models for healthcare.
method Feature-sparse Generalized Additive Model combining feature selection and interpretable prediction.
result DyS model outperforms other survival analysis models in interpretability and accuracy.
BICauseTree improves causal effect estimation by identifying clusters and balancing treatment allocation.
problem Improving interpretability and transparency in causal effect models from observational data.
method Hierarchical bias-driven stratification using decision trees with a customized objective function.
result BICauseTree provides interpretable causal effect estimation and is comparable to existing methods.
Study explores fairness in financial deep learning through multi-scale trust quantification.
problem Ensuring fairness in financial deep learning models, especially under regulatory compliance.
method Conducts multi-scale trust quantification on a deep neural network for credit card default prediction.
result Demonstrates the feasibility and utility of multi-scale trust quantification for financial deep learning fairness.
SMILE improves explainability of machine learning models.
problem Difficulty in understanding and trusting the conclusions of black-box machine learning models.
method Statistical Model-agnostic Interpretability with Local Explanations (SMILE).
result SMILE makes machine learning models more interpretable.
Paper introduces a method to interpret complex epidemiology simulators.
problem Difficult interpretation of stochastic epidemiology simulators.
method Hijacking internal random number generators with probabilistic programming.
result Restores trust between policymakers and simulators by providing insights.
Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user. There are a plethora of existing solutions addressing various aspects of interpretability ranging from identifying …
Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user interfaces. Thus, interpretability has become a vital concern in machine learnin…
A framework uses preprocessing to improve psychiatric questionnaire predictions while maintaining interpretability.
problem Weak predictive accuracy and limited interpretability of psychiatric questionnaires.
method Two-stage method: stable preprocessing followed by a linear mapping.
result REFINE outperforms other interpretable approaches in psychiatric and non-psychiatric prediction tasks.
Method extracts time-localized clusters to explain deep learning models in ECG analysis.
problem Limited understanding of deep learning models in ECG analysis.
method Extracts time-localized clusters from model's internal representations.
result Enhances trust in AI-driven diagnostics and reveals clinically relevant patterns.
DeFi doesn't fully remove trust, showing run risk and personal character's importance.
problem The need for trust in DeFi despite its code-based approach.
method Natural experiment revealing identities of DeFi participants, including a criminal.
result DeFi doesn't fully remove trust, showing run risk and personal character's relevance.