Explains deep neural networks using new interpretation techniques.
problem Interpreting and understanding deep neural networks.
method Introduces new techniques for interpretation and practical applications.
result Efficient use of interpretation techniques on real data.
GENESIM creates interpretable models with improved predictive performance.
problem Overfitting in decision trees leads to poor predictive performance and lack of interpretability.
method GENESIM uses a genetic algorithm to transform an ensemble of decision trees into a single interpretable model.
result GENESIM achieves better predictive performance than decision tree induction and ensemble techniques, while maintaining interpretability.
Survey on techniques to make machine learning models understandable.
problem Humans cannot understand complex machine learning model decisions.
method Survey of existing techniques to increase interpretability.
result Challenges and achievements in interpretable machine learning need further exploration.
Proposes FairCORELS for fair, interpretable rule lists.
problem Fairness in interpretable models for high-stakes decisions.
method Multi-objective variant of CORELS, supporting fairness measures.
result Outperforms state-of-the-art fair classification techniques.
The paper uses SHAP for interpreting machine learning models in hospital data.
problem Interpreting machine learning models in healthcare.
method SHAP for feature importance and feature packing techniques.
result SHAP provides better interpretability of machine learning models in healthcare.
Model-agnostic interpretation methods can mislead if not used carefully.
problem Misinterpretation of machine learning models due to improper use of techniques.
method General pitfalls of model-agnostic interpretation methods.
result Many pitfalls exist when using global interpretation techniques for machine learning models.
Interpretable ML helps discover insights from big data.
problem Validating data-driven discoveries from complex datasets.
method Statistical and machine learning techniques for interpretable models.
result Challenges in validating data-driven discoveries remain.
API technique improves multiclass GAM interpretability.
problem Interpretability breakdown in multiclass GAMs.
method Developed two axioms and API technique for multiclass GAMs.
result API technique transforms multiclass GAMs to be visually interpretable.
The study explores statistical methods to interpret radiological models and identify key features.
problem Interpreting complex radiological models for clinical use.
method Exploration of statistical techniques to assess relationships between radiomic features.
result Identification of key relationships and features for improved interpretability.
The paper investigates interpretability techniques for deep learning models in medical data.
problem Understanding the logic behind predictions of black-box models in medical decision-making.
method Applied deep neural networks and random forests to a medical dataset. Used autoencoders and local interpretable models to provide insights.
result Local interpretable models and autoencoders provide meaningful insights into cancer predictions, identifying distinct and non-generalizable features.
This paper explores causal analysis in machine learning for better interpretability.
problem The lack of causality in traditional interpretable machine learning models.
method An overview of causal approaches for interpretable machine learning.
result Causal analysis improves the interpretability of machine learning models.
This paper reviews methods for interpreting deep learning models with sequential data.
problem Limited interpretability of deep learning models in sequential data domains.
method Reviews and compares techniques for sequential interpretability.
result Current techniques have limitations and future research is needed.
Gradient Weighted Superpixels improve CNN interpretability without sacrificing speed.
problem Efficiency vs. interpretability trade-off in CNNs, especially for large input volumes.
method Gradient-based pixel scoring techniques applied to superpixels.
result Superpixels approximate LIME in a fraction of the time, improving interpretability.
This paper explores how to interpret machine learning models in business process analytics.
problem The lack of interpretability in machine learning models used for predictive process analytics.
method Derives explanations using interpretable machine learning techniques to compare and contrast predictive models.
result Highlights scenarios where accuracy alone may not be sufficient in assessing the suitability of techniques used to encode event log data.
Interpretable classifier improves accuracy through probability series expansion.
problem Improving classifier accuracy while maintaining interpretability.
method Directly measures class probabilities from training data, refines predictions through series expansion.
result Achieves comparable accuracy to Random Forests on four datasets.
Unified framework for interpreting complex regression models with many predictors.
problem Interpreting nonparametric regression models with many predictors.
method Derivative-based approach for existing tools like partial-dependence plots.
result New technique called accumulated total derivative effects plot for complex models.
The paper tackles inconsistency in removal-based explanations and proposes methods to reduce it.
problem Inconsistency in removal-based explanations.
method Established the Impossible Trinity Theorem and proposed two novel algorithms to minimize interpretation error.
result The proposed methods achieve a substantial reduction in interpretation error, up to 31.8 times lower.
TimeTrail detects financial fraud patterns through temporal correlation analysis.
problem Detecting and explaining complex financial fraud patterns.
method Temporal data enrichment, dynamic correlation analysis, interpretable pattern visualization.
result TimeTrail outperforms conventional methods in accuracy and interpretability.
Unified framework for interpreting any predictive model.
problem Difficulty in comparing and understanding various model-agnostic interpretation techniques.
method SIPA (sampling, intervention, prediction, aggregation) framework
result Unified terminology and methodology for interpreting predictive models.
This paper explores how cognitive biases impact human understanding of rule-based machine learning models.
problem The impact of cognitive biases on human interpretation of machine learning models.
method A review of 20 cognitive biases and their effects on human understanding of machine learning models.
result Cognitive biases significantly affect human understanding of interpretable machine learning models, particularly logical rules.
Overview of SML techniques with banking applications.
problem Credit risk modeling in banking.
method Tree-based ensemble algorithms, Feedforward NNs, hyper-parameter optimization, machine learning interpretability.
result Comparison of ML algorithm features and their application in banking.
Novel technique detects adversarial samples in face recognition models.
problem Widespread adversarial sample attacks on DNN models.
method Bi-directional correspondence inference between attributes and internal neurons to identify critical neurons.
result 94% detection accuracy for 7 different kinds of attacks with 9.91% false positives.
Improves interpretability of graph representation learning models.
problem Limited insight into graph representation learning models.
method Exploration of methods to interpret node embeddings and creation of an evaluation framework.
result Improved ability to recover graph structure in downstream tasks.
Proposes a technique to interpret deep learning models by generating counterfactual inputs.
problem Understanding and explaining the decisions made by deep neural networks.
method Uses a generative model to edit input images and generate counterfactual scenarios for model interpretation.
result Demonstrates the effectiveness of the introspection approach on MNIST and CelebA datasets.
Survey of deep learning methods for medical anomaly detection.
problem Medical anomaly detection using machine learning.
method Thorough review of deep learning techniques across various medical domains.
result Comparison and contrast of deep learning models and their limitations.
New method visualizes decision boundaries of classification models.
problem Difficulty in understanding how classification models interpret data.
method Hybrid supervised-unsupervised technique for visualizing decision boundaries.
result Provides interpretable maps for qualitative and quantitative analysis.
Empirical study shows interpretable gradients improve adversarial robustness.
problem Connecting adversarial robustness and model interpretability.
method Introduced Interpretation Regularization (IR) to encourage interpretable gradients.
result Training models to have interpretable gradients improves adversarial robustness.
Improved KernelSHAP via linear regression for ML model interpretation.
problem Efficiently estimating Shapley values in model-agnostic settings.
method Revisiting KernelSHAP via linear regression, developing techniques for convergence and uncertainty.
result Original KernelSHAP incurs negligible bias for significant variance reduction.
The paper proposes a method to calibrate healthcare AI models for reliability and interpretability.
problem Characterizing model reliability and enabling introspection of model behavior in clinical decision making.
method A calibration-driven learning method combined with interpretability techniques based on counterfactual reasoning.
result Demonstrates the effectiveness of the proposed approach using a lesion classification problem with dermoscopy images.
New technique learns STL formulas for classifying time-series data.
problem Lack of interpretability in traditional machine learning for time-series data.
method Systematically explores the space of all STL formulas, prunes the space, and learns semantically equivalent formulas.
result Automatically learns STL formulas for clustering and classifying real-valued time-series data.
Technique creates highly accurate small models for better interpretability.
problem Balancing model accuracy and interpretability for constrained models.
method Identifies optimal training distribution for a given model size using Infinite Mixture Model with Beta components and Bayesian Optimization.
result Significant improvements in F1-score, up to 100% in some cases.
LionForests interprets random forests for better understanding of predictions.
problem Interpreting black-box tree ensemble models like random forests.
method Combining unsupervised learning and a similarity metric to explain tree ensembles.
result LionForests provides transparent rules for interpreting random forest predictions.
The paper defines and learns credible models that are both accurate and interpretable.
problem Models may be interpretable but lack credibility when their reasoning does not align with established knowledge.
method Formally defines credibility, proposes EYE penalty that incorporates expert knowledge.
result Models learned with EYE penalty are significantly more credible than those learned with other penalties.
Biophysical models explain deep learning in gene regulation.
problem Difficulty in interpreting deep learning models in gene regulation.
method Expressed biophysical models as neural networks with explicit interpretations.
result Biophysical networks can be inferred from MPRAs.
New method uses prediction uncertainties to improve deep learning model interpretation.
problem Improving deep learning model interpretation and generalization.
method Introducing a new regularization that considers both mean and variance of predictions, and a technique to explain input uncertainties.
result Improved generalization and new ways to validate and interpret deep learning models.
Paper optimizes traffic signal control for better traffic flow.
problem Optimizing traffic signal control to reduce congestion and improve safety.
method Value-based reinforcement learning with interpretable policy functions (polynomial functions).
result Deep Regulatable Hardmax Q-learning variant reduces vehicle delay by up to 19.4%.
Workshop reviews techniques to understand neural NLP models.
problem Understanding the inner workings of neural networks in natural language processing.
method Systematic manipulation of inputs, decoding intermediate representations, modifying architectures, and testing on simplified languages.
result Various techniques can improve explainability of neural network models.
Study compares feature selection methods for stress hotspot classification.
problem Optimizing feature selection for stress hotspot classification in materials.
method Applied various feature selection methods to microstructural data.
result Demonstrated some feature selection techniques are biased, highlighting a preferred method.
InterpretML simplifies machine learning interpretability for users and researchers.
problem Making machine learning models understandable to non-experts.
method Unified Python package exposing interpretability algorithms and visualization.
result First implementation of Explainable Boosting Machine, a powerful, interpretable model.
Neural networks improve geoscience by enabling interpretable decision pathways.
problem Lack of methods to interpret neural networks' learning and decision-making.
method Backwards optimization and layerwise relevance propagation.
result Interpretation techniques reveal meaningful connections in geoscientific data.
iLED framework offers interpretable dynamics for multiscale systems.
problem Modeling high-dimensional multiscale systems is challenging.
method Interpretable Learning Effective Dynamics (iLED) framework based on Mori-Zwanzig and Koopman operator theory.
result Comparable accuracy to state-of-the-art approaches with added interpretability.
The paper certifies decision trees against evasion attacks using program analysis.
problem Vulnerability of decision tree models to evasion attacks by maliciously crafted perturbations.
method Transform decision trees into imperative programs for program analysis, leveraging abstract interpretation.
result Soundly verifies security guarantees of decision tree models, yielding minimal false positives.
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…
The paper reviews machine learning safety techniques for autonomous vehicles.
problem Challenges in machine learning safety for autonomous vehicles.
method Organizes practical safety techniques to complement engineering safety.
result Enhances dependability and safety of machine learning algorithms in autonomous vehicles.
Scalable solution for interpreting complex data-driven models.
problem Interpreting black box models and handling large datasets.
method Streaming neighborhood graph construction, topology computation, and data aggregation.
result Interactive exploration of high-dimensional data.
The paper addresses interpretability issues in EBM models by improving feature selection and reducing spurious interactions.
problem Interpretability issues in EBM models, especially spurious interactions and single feature dominance.
method Alternate Cross-feature selection, ensemble features, and model configuration alteration techniques.
result Our approach improves interpretability and predictive performance of EBM models, reducing spurious interactions and single feature dominance.
Machine learning speeds BSM data interpretation at LHC.
problem Challenging to scan high-dimensional BSM theories due to expensive simulations.
method Machine learning to predict BSM theory parameters from data.
result Predicts natural SUSY events up to 4 orders of magnitude faster.
New insights into ML models' accuracy and generalization for scientific problems.
problem Quantifying accuracy and generalization of ML models in scientific applications.
method Rigorous numerical analysis and theoretical bounds for linear differential equations.
result Different ML models can have opposing generalization behaviors, contrary to intuition.