Improved local explainer aggregation for interpretable machine learning models.
problem Improving the interpretability of black box machine learning models.
method Non-convex optimization and integer optimization framework for local explainer aggregation.
result Our method outperforms existing methods in terms of coverage and fidelity, particularly in multi-class settings.
Optimal allocation between explainable and black box models for high performance and explainability.
problem Balancing explainability and performance in model ensembles.
method Optimal allocation of observations between explainable and black box models to maximize ensemble performance and explainability.
result Learned allocations maintain high ensemble performance and explainability, sometimes outperforming individual models.
Defines globalness measure for explainers using optimal transport.
problem Challenges in evaluating and comparing explainability methods.
method Axiomatic definition and proof of Wasserstein Globalness measure.
result Wasserstein Globalness measure facilitates meaningful comparison and selection of explainers.
Proposes counterfactual explainability for causal attribution, extending variance analysis methods.
problem Lack of mechanistic understanding in existing tools for explaining complex models.
method Extends global sensitivity analysis methods to causal explanations using directed acyclic graphs.
result Developed methods to estimate counterfactual explainability and applied to income inequality analysis.
This paper reviews methods to improve AI explainability in finance.
problem Lack of explainability in AI models, especially in finance.
method Categorizes methods to improve explainability of deep learning models.
result Provides a comparative survey of methods to enhance AI explainability.
Artificial Intelligence (AI) has become an integral part of domains such as security, finance, healthcare, medicine, and criminal justice. Explaining the decisions of AI systems in human terms is a key challenge--due to the high complexity of the model, as well as the potential implications on human interests, rights, …
New method explains predictive uncertainty by focusing on second-order effects.
problem Explaining predictive uncertainty in machine learning models.
method CovLRP, CovGI, etc., based on second-order effects.
result Predictive uncertainty is dominated by second-order effects.
New method explains survival analysis models using median-SHAP.
problem Need for explainable AI in medical applications, especially for survival analysis.
method Introduces median-SHAP for explaining survival analysis models.
result Conventionally used mean anchor point can lead to misleading interpretations; median-SHAP provides a better approach.
New method explains high-dimensional text classifiers.
problem Limited explainability tools for high-dimensional inputs and neural networks.
method Theoretical high-dimensional properties in neural networks.
result Improved explainability for neural network classifiers.
XEM improves multivariate time series classification with explainable models.
problem Multivariate time series classification challenges.
method Hybrid ensemble method combining explicit boosting-bagging and implicit divide-and-conquer.
result XEM outperforms state-of-the-art MTS classifiers on public datasets.
New framework assesses and benchmarks ML methods for multivariate time series.
problem Benchmarking and explaining performance of machine learning methods.
method Proposes a new framework with systematized performance-explainability characteristics.
result Illustrates application to multivariate time series classifiers.
Study examines explainable machine learning for monotonic models, finding Integrated gradients better for strong monotonicity.
problem Applying explainable machine learning to science-informed models.
method Proposed axioms for monotonicity, tested Shapley value and Integrated gradients methods.
result Integrated gradients provides better explanations for strong monotonicity.
Develops a measure for subjective explainability of ML predictions.
problem Ensuring transparency and trust in automated decision-making.
method Information-theoretic concepts applied to conditional entropy of predictions given user feedback.
result EERM principle balances subjective explainability and risk.
Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactual explanations, or influential training data. Yet there is little understanding of how organizations use these methods in practice. This st…
A new method explains mixed features for predictive models using conditional inference trees.
problem Explaining complex machine learning models with mixed features.
method Proposes a method to explain mixed features (continuous, discrete, ordinal, categorical) using conditional inference trees.
result Our method often outperforms current industry standards in various simulation studies and real-world financial data.
Recent work has shown great promise in explaining neural network behavior. In particular, feature attribution methods explain which features were most important to a model's prediction on a given input. However, for many tasks, simply knowing which features were important to a model's prediction may not provide enough …
Combines Integrated Gradients and PatternAttribution into PGIG, outperforming alternatives.
problem Improving neural network explainability methods.
method Combines Integrated Gradients and PatternAttribution into Pattern-Guided Integrated Gradients (PGIG).
result PGIG outperforms other explainability methods in a large-scale image degradation experiment.
Networks are powerful data structures, but are challenging to work with for conventional machine learning methods. Network Embedding (NE) methods attempt to resolve this by learning vector representations for the nodes, for subsequent use in downstream machine learning tasks. Link Prediction (LP) is one such downstream…
ALMANACS benchmarks explainability methods on simulatability.
problem Evaluating the effectiveness of explainability methods for language models.
method ALMANACS is a simulatability benchmark that evaluates explainability methods on twelve safety-relevant topics.
result No explainability method outperforms the explanation-free control across all topics.
ExKMC improves explainable k-means clustering by balancing accuracy and simplicity.
problem Limited explainable methods for unsupervised learning.
method Develops ExKMC, a new algorithm that uses a decision tree with k′ leaves to explain k-means clustering, trading explainability for accuracy. result ExKMC produces a low-cost clustering that outperforms existing methods.
Proposes a method for explaining tabular data using copulas.
problem Lack of ground truth for explainability in complex datasets.
method Uses copulas to specify statistical properties and build intuition.
result Demonstrates improved explainability on logistic regression and correlation use cases.
Method trains deep models to explain predictions with fewer examples.
problem Difficulty in humans understanding deep model predictions.
method Simultaneously trains prediction and explanation models with sparse regularization.
result Improves faithfulness of explanations with fewer examples while maintaining predictive performance.
Proposes a simple method to explain aleatoric uncertainty in neural networks.
problem Lack of transparent explanations for uncertainty estimates in AI models.
method Adapting a neural network with Gaussian output to estimate predictive variance and applying explainers to the variance output.
result The proposed method explains uncertainty more reliably than complex approaches and outperforms them in most settings.
SurvBeNIM explains survival models using neural networks.
problem Explaining predictions of survival models.
method Extends Beran estimator with neural importance functions.
result Improved explanation of survival models compared to existing methods.
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explaine…
This work explores explainability in quantum machine learning.
problem Limited understanding of quantum machine learning models.
method Identifies research avenues and proposes two explanation methods.
result Provides a clear perspective on explainability in quantum learning.
EXoN creates an explainable latent space for semi-supervised learning.
problem Creating an explainable latent space for semi-supervised learning.
method EXoN combines VAE with SCI (Soft-label Consistency Interpolation) to create an explainable latent space.
result EXoN reduces the cost of investigating representation patterns on the latent space.
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.
This review explores methods to explain deep neural networks and their applications.
problem Understanding the decision-making process of deep neural networks.
method Overview of interpretability methods, theoretical foundations, and comparative evaluations.
result Demonstrates the effectiveness of explainable AI in various applications.
As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developer…
SurvLIME explains survival models by approximating them with Cox models.
problem Explaining complex survival models in machine learning.
method Applies Cox proportional hazards model to approximate survival model locally.
result Demonstrates efficiency through numerical experiments.
Enhances explainability of AI models without sacrificing accuracy.
problem Lack of interpretability in black-box models like Deep Neural Networks and Gradient Boosting.
method Co-supervised Local Model Synthesis (SynthTree) using Mixture of Linear Models (MLM).
result Statistical models significantly enhance explainability of AI models.
New methods for explaining Random Forest predictions using case-based reasoning.
problem Lack of explainability for black-box machine learning models like Random Forests.
method Extracting distance metric from Random Forests to identify prototypes, critics, counter-factuals, and semi-factuals.
result Identified special points from training datasets to explain Random Forest predictions.
TimeVQVAE-AD detects anomalies in time series data with high accuracy and provides explainable results.
problem Detecting and explaining anomalies in time series data accurately.
method Masked latent generative modeling in time-frequency domain.
result TimeVQVAE-AD outperforms existing methods in anomaly detection and explainability.
Study evaluates feature ranking methods' faithfulness in ML models, improving with dimensionality reduction.
problem Quantifying and improving the faithfulness of feature ranking methods in ML models.
method Evaluation of multiple feature ranking methods, including SHAP, LIME, ALE variance, and LR coefficients, using permutation importance as a baseline.
result Dimensionality reduction improves the faithfulness of feature ranking methods, making permutation importance the most faithful method.
DILP improves fraud detection explainability without significant performance boost.
problem Improving fraud detection explainability in machine learning.
method Differentiable Inductive Logic Programming (DILP) for fraud detection with data curation.
result DILP provides comparable results to traditional methods but lacks significant advantage.
Anchors explains text classifiers by highlighting key words.
problem Interpreting machine learning models, especially for text classifiers.
method Formalizes Anchors' algorithm and analyzes its behavior on linear text classifiers.
result Anchors produces meaningful results on linear text classifiers.
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.
Interactive EMA combines multiple explainability methods to improve model understanding.
problem Isolated explanations of machine learning models lead to misunderstandings and wrong reasoning.
method Interactive EMA (IEMA) combines multiple explainability methods sequentially.
result Interactive EMA increases the performance and confidence of human decision making.
We adapt Shapley values to explain model uncertainty, connecting it to information theory.
problem Explaining uncertainty in model predictions.
method Adapted Shapley value framework to quantify feature contributions to predictive uncertainty.
result Deep connections between Shapley values and information theory quantities.
New method improves model explainability.
problem Improper model explanations fail to reflect true data-generating process.
method Shapley Marginal Surplus for Strong Models
result Significant outperformance in inferential capabilities.
Paper bridges generative models and explainability.
problem Lack of connection between generative models and explainability.
method Proposes a probabilistic framework for example-based explanations.
result Formally defines example-based explanations for deep generative models.
Paper describes anomaly detection and explainability for multivariate functional data.
problem Anomaly detection and explainability in multivariate functional data.
method Transform series into features, use Isolation Forest, compute SHAP coefficients, and use supervised decision tree.
result Method performs well on simulated and real industry data.
This guide simplifies explainable deep learning for beginners.
problem Difficulty in understanding deep learning model decisions.
method Introduces three dimensions for explainable deep learning methods.
result Clarifies evaluations for model explanations.
Unified framework for model explanation methods based on feature removal.
problem Unclear relationships and preferences among various model explanation methods.
method Characterizes removal-based explanations along three dimensions.
result Unified 26 existing methods, including widely used approaches.
Most accurate recommender systems are black-box models, hiding the reasoning behind their recommendations. Yet explanations have been shown to increase the user's trust in the system in addition to providing other benefits such as scrutability, meaning the ability to verify the validity of recommendations. This gap bet…
We are used to the availability of big data generated in nearly all fields of science as a consequence of technological progress. However, the analysis of such data possess vast challenges. One of these relates to the explainability of artificial intelligence (AI) or machine learning methods. Currently, many of such me…
SMT-EX enhances SMT for explaining surrogate models of mixed-variable design problems.
problem Making decisions and understanding complex systems using surrogate models of mixed-variable design problems.
method Integrates explainability techniques into SMT, including Shapley Additive Explanations, Partial Dependence Plot, and Individual Conditional Expectations.
result Demonstrates versatility in addressing diverse problem characteristics.