Generative Adversarial Network (GAN) generates user-friendly explanations for loan denials.
problem Lack of explainable AI for financial services, especially in loan denials.
method Developed a GAN to generate explanations for loan denials, using a representative dataset.
result Demonstrated the GAN can generate explanations for various stakeholders, including applicants and decision makers.
ProSeNet provides interpretable deep sequence models with natural explanations.
problem Challenges in explaining deep neural network predictions for sequence modeling.
method Prototypes derived from case-based reasoning, with criteria for simplicity, diversity, and sparsity.
result Achieves accuracy on par with state-of-the-art models while providing interpretable explanations.
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.
We define and compute plausible counterfactual explanations using density constraints.
problem Efficiently compute plausible counterfactual explanations for machine learning models.
method Propose and study a formal definition of plausible counterfactual explanations, use density estimators, and introduce convex density constraints.
result Convex density constraints ensure plausible and feasible counterfactual explanations.
Proposes a new method for better explaining neural network decisions.
problem Challenges in explaining neural network decisions due to base-point choice.
method Introduces tangentially aligned integrated gradients to maximize explanation tangential alignment.
result Optimal base-point maximizes explanation tangential alignment, leading to more accurate interpretations.
Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a comprehensive understanding of the achievements and challenges is still lacking…
CrystalCandle creates user-friendly explanations for machine learning models.
problem Low trust in predictive models due to lack of interpretability.
method End-to-end pipeline for model interpretation, including Model Importer, Interpreter, Narrative Generator, and Exporter.
result CrystalCandle leads to higher adoption rates and improved downstream metrics.
Paper speeds up large foundation models for time series data.
problem Resource-intensive foundation models limit accessibility.
method Dimensionality reduction techniques, including PCA and neural network adapters.
result Up to 10x speedup and 4.5x more datasets fit on a single GPU.
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.
Advocates for user-friendly RL problem descriptions to improve usability and generalization.
problem Usability and generalization challenges in RL for non-engineers.
method Development of user-friendly description languages for RL problems.
result Improved ability of RL algorithms to generalize to new problems.
STOOD-X detects out-of-distribution samples without distributional assumptions and provides explainable visualizations.
problem Challenges in OOD detection, including restrictive assumptions, scalability issues, and lack of interpretability.
method Two-stage methodology combining statistical nonparametric test and explainability enhancements.
result Achieves competitive performance in high-dimensional and complex settings, with explainability framework enabling human oversight.
A user-friendly interface constructs effective background knowledge from ER diagrams.
problem Inefficient construction of background knowledge by domain experts in ILP systems.
method Design of a graphical user interface to interact with Entity Relationship diagrams to construct modes for a probabilistic logic learning system.
result Domain experts can construct effective background knowledge on par with experts using the graphical interface.
A simplified, user-friendly repackaging of the curvature estimates implied by the Seiberg-Witten equations is formulated in terms of the convex hull of the set of monopole classes. New results are also obtained concerning boundary cases of the resulting forms of the curvature estimates.
EvaSylv software evaluates forest management with natural risk considerations.
problem Evaluating forest management under increased natural risk due to climate change.
method User-friendly software simulates forest management scenarios, integrating natural risk using a Poisson process and Faustmann approach.
result Software optimizes forest management criteria like Faustmann value and Averaged yield value.
S-SIRUS explains RF for spatial data, improving accuracy and interpretability.
problem Non-interpretable nature of Random Forest in spatially dependent data.
method Proposes S-SIRUS, a spatial extension of SIRUS for extracting interpretable rules.
result S-SIRUS outperforms SIRUS in spatially dependent data, offering higher predictive accuracy and shorter rule lists.
Flexible Cox model for time-dependent covariates with complex sparsity patterns.
problem Lack of flexibility in enforcing specific sparsity patterns in time-dependent Cox models.
method Proposes a flexible framework for variable selection in time-dependent Cox models, accommodating complex selection rules.
result Achieves accurate estimation with low false alarm rates for complex covariate structures.
RNNs are competitive but not as user-friendly as ETS and ARIMA.
problem Improving RNNs for non-expert users.
method Empirical study and open-source framework of RNN architectures.
result RNNs can model seasonality directly if the series have homogeneous patterns.
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
We prove that every Legendrian knot in the tight contact structure of the 3-sphere is determined by the contactomorphism type of its exterior. Moreover, by giving counterexamples we show this to be not true for Legendrian links in the tight 3-sphere. On the way a new user-friendly formula for computing the Thurston-Ben…
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
Survey on efficient counterfactual explanations for various ML models.
problem Providing understandable explanations for machine learning predictions.
method Review and propose methods for computing counterfactual explanations.
result Efficient methods for various ML models and new methods for unconsidered models.
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
Two effective methods for writing the dynamical equations for non-holonomic systems are illustrated. They are based on the two types of representation of the constraints: by parametric equations or by implicit equations. They can be applied to linear as well as to non-linear constraints. Only the basic notions of vecto…
Efficiently computes counterfactual explanations for LVQ models.
problem Need to efficiently explain predictions of machine learning models.
method Derives convex and non-convex programs for LVQ models.
result Efficient computation of counterfactual explanations for LVQ models.
Model explanations can leak sensitive training data information, posing privacy risks.
problem Privacy risks of model explanations that expose training data information.
method Membership inference attacks on feature-based model explanations.
result Backpropagation-based explanations reveal statistical information about decision boundaries, leaking training data membership.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
Paper proposes metrics to evaluate AI explanations without ground truth.
problem Challenges in evaluating neural network explanations without ground truth.
method Designs four metrics to evaluate explanation results.
result New insights into neural network interpretation methods.
We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while…
Paper simplifies concentration inequalities for easier probabilistic analysis.
problem Complexity in probabilistic analysis of random variables.
method Compact notations for concentration inequalities.
result Simplified expressions for typical sizes and tails of random variables.
For a given cusped 3-manifold M admitting an ideal triangulation, we describe a method to rigorously prove that either M or a filling of M admits a complete hyperbolic structure via verified computer calculations. Central to our method are an implementation of interval arithmetic and Krawczyk's Test. These techni…
Paper explores a consumer-friendly approach to explain machine learning decisions.
problem Challenges in providing understandable explanations for machine learning predictions.
method Consumer-driven approach called TED that asks for explanations in training data.
result TED is robust to increasing numbers of explanations, noisy explanations, and missing explanations.
Formalizes explanations as blending input and model output.
problem Creating clear and consistent explanations for model predictions.
method Defines properties of explanation functions and links them to model layers.
result Consistency of activations across layers implies consistency of explanations.
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
G-SHAP generates multiple types of explanations for machine learning models.
problem Understanding model predictions and their differences across groups.
method Generalization of SHAP method to produce additional types of explanations.
result G-SHAP produces explanations for classification, intergroup differences, and model failure.
LLMs' explanations are often insufficient and vary with input distribution.
problem Evaluating the sufficiency of LLM explanations without predefined biases.
method Generalizing sufficiency to arbitrary explanations, using LLM's input beliefs, and introducing SCSuff metric.
result Explanation sufficiency can vary with input distribution and is weakly correlated with model size, accuracy, or output entropy.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
problem Measuring the impact of visual explanations on human accuracy and trust in model predictions.
method Randomized controlled trial with image-based age prediction task, varying levels of explanation quality.
result Visual explanations do not significantly alter human accuracy or trust in the model.
Manipulated explanations can be made imperceptible to the naked eye.
problem The trustworthiness and interpretability of neural networks can be compromised by manipulable explanations.
method The paper demonstrates that explanations can be altered by applying small, imperceptible input changes that do not affect the network's output.
result An upper bound on the susceptibility of explanations to manipulation has been derived, and effective mechanisms to enhance explanation robustness have been proposed.
Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. Our contributions in this paper are twofold. First, we investigate schemes to combine explanation methods and reduce model uncertainty to obtain a sing…
The paper introduces a new framework for making machine learning explanations more understandable to humans.
problem Making machine learning explanations comprehensible and aligned with human preferences.
method Inspired by philosophy, cognitive science, and social sciences, the paper formalizes a framework using the concept of 'weight of evidence' from information theory.
result The framework produces intuitive and comprehensible explanations that align with human preferences.
Proposes a method to generate counterfactual and contrastive explanations using SHAP.
problem Need for explainable AI and legal requirement for model interpretability.
method Model agnostic method using SHAP to generate contrastive and counterfactual explanations.
result Demonstrates effectiveness of the method on various datasets.
Managing large-scale transportation infrastructure projects is difficult due to frequent misinformation about the costs which results in large cost overruns that often threaten the overall project viability. This paper investigates the explanations for cost overruns that are given in the literature. Overall, four categ…
Unified techniques improve stability and replicability in changing data.
problem Concept drift in data generating distribution.
method Removing hidden confounding and causal regularization.
result Improves stability, replicability, and robustness in heterogeneous data.
This research investigates reliable local explanations for machine listening models.
problem Generating reliable local explanations for machine listening models.
method Investigates the sensitivity of SoundLIME explanations to input perturbations and proposes a novel method for identifying suitable content types.
result SoundLIME explanations are sensitive to the content in occluded input regions, and the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.
Defines explanations for classifier outcomes using causal concepts.
problem Understanding classifier outcomes in a causal context.
method Proposes a new definition of explanation based on causality, compares it with existing notions, and evaluates it experimentally.
result Experimental evaluation shows the new definition's effectiveness on financial datasets.
This research improves interpretability in sequential explanations using mental models.
problem Improving interpretability in sequential explanations between two parties.
method A reinforcement learning framework that selects explanations based on the explainee's mental model.
result Mental model-based policies increase interpretability over random selection in multiple sequential explanations.