This research examines how model explanations change under distribution shifts in tabular data.
problem Detecting distribution shifts in tabular data affecting model performance and explanations.
method Investigates the relationship between model performance and explanation characteristics under distribution shifts.
result Explanation shifts are a better indicator for detecting predictive performance changes than traditional distribution shift techniques.
Study shows explanation disparities in machine learning models are influenced by data and model properties.
problem Disparities in post-hoc machine learning explanation methods across race and gender.
method Simulations and experiments on a real-world dataset to assess challenges to explanation disparities.
result Increased covariate shift, concept shift, and omission of covariates increase explanation disparities, especially for neural network models.
New approach models how explanations shift with distribution changes.
problem Model performance drops with changing input data distributions.
method Models explanation shifts and compares them to state-of-the-art techniques.
result Modeling explanation shifts better detects out-of-distribution behavior.
Neural networks memorize exceptions, leading to poor generalization.
problem Memorization of exceptions hinders neural network generalization.
method Formalized memorization-generalization interplay, proposed MAT to shift logits.
result MAT improves generalization by learning robust patterns invariant across distributions.
New insights into how high-dimensional models handle covariate shifts.
problem Covariate shift in high-dimensional random feature regression.
method Exact high-dimensional asymptotics of random feature regression under covariate shift.
result Overparameterized models exhibit enhanced robustness to covariate shift.
ShapShift explains shifts in model predictions due to data distribution changes.
problem Prediction shifts caused by changes in input distribution.
method Subgroup Conditional Shapley Values applied to decision trees and ensembles.
result Simple, faithful, and near-complete explanations of prediction shifts across model classes.
Unified framework certifies predictor performance under distribution shift.
problem Certifying predictor performance under distribution shift.
method Unified framework with explicit inequalities, sound verification, and identifiable structure.
result Explicit upper bound on excess risk under shift.
Paper proposes Coalitional BAE to improve explainability of unsupervised deep learning models.
problem Improving explainability of Autoencoder's predictions.
method Introduces Coalitional BAE, inspired by agent-based system theory, to reduce correlation in explanations.
result Improved quality of explanations using Coalitional BAE on publicly available datasets.
Proposes minimal interventions over counterfactual explanations for algorithmic recourse.
problem Lack of actionable recommendations for algorithmic recourse.
method Causal reasoning to shift focus from explanations to recommendations.
result Minimal interventions provide more actionable recommendations for recourse.
End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relyi…
New metric assesses reliability of AI explanations.
problem Unreliable AI explanations under realistic conditions.
method Explanation Reliability Index (ERI) metrics quantifying stability under four axioms.
result Widespread reliability failures in popular explanation methods.
RAW-Explainer generates interpretable subgraph explanations for link predictions in knowledge graphs.
problem Interpreting GNN predictions for link prediction in heterogeneous settings is challenging.
method RAW-Explainer uses random walk objective and neural network to generate connected, concise subgraph explanations.
result RAW-Explainer strikes a balance between explanation quality and computational efficiency.
New method improves model reconstruction using counterfactuals and polytope theory.
problem Reconstructing models with minimal input changes and avoiding decision boundary shifts.
method Using polytope theory to derive loss functions that treat counterfactuals differently from ordinary instances.
result Improves fidelity between target and surrogate model predictions on multiple datasets.
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.
Researchers show how to manipulate Partial Dependence plots to deceive explanations of predictive models.
problem The robustness and trustworthiness of Partial Dependence (PD) explanations are compromised.
method Data poisoning using genetic and gradient algorithms to manipulate PD plots.
result PD explanations can be fooled and manipulated to mislead understanding of predictive models.
Unified framework for distribution shift estimation, explanation, and improvement.
problem Estimating, explaining, and improving model performance on target domains with distribution shift.
method Entropic Projection Alignment (EPA) aligns source and target distributions by matching moments and minimizing KL divergence.
result EPA consistently outperforms state-of-the-art baselines while offering computational efficiency.
FIT evaluates time series model feature importance quantifying distributional shift.
problem Lack of explanations for time series models in high-stakes applications.
method FIT framework quantifies feature importance based on distributional shift using KL-divergence.
result FIT identifies important time points and observations superiorly compared to baselines.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
Paper proposes MMD-Sense-Analysis for detecting word sense shifts.
problem Detecting and interpreting shifts in word meanings over time.
method Leverages Maximum Mean Discrepancy (MMD) to identify and explain word sense changes.
result Demonstrates effectiveness of MMD-Sense-Analysis through empirical results.
This paper introduces DCE for better counterfactual explanations using optimal transport.
problem Lack of nuanced distributional characteristics in existing counterfactual explanations.
method Formulates a chance-constrained optimization problem using optimal transport to derive counterfactual distributions.
result DCE provides deeper insights into decision-making models by aligning counterfactual distributions with factual ones.
Minimal token perturbations reveal how Transformer models process information.
problem Understanding information propagation in Transformer models for interpretability.
method Study of minimal token perturbations on embedding space.
result Rare tokens cause larger shifts, and input information mixes deeper.
Public pretraining improves private model training even in extreme distribution shift scenarios.
problem Improving private model training accuracy in settings with large distribution shift.
method Empirical evaluation and theoretical explanation of public representations improving private training accuracy.
result Public representations can improve private training accuracy by up to 67% over private training from scratch in settings with large distribution shift.
Conformal prediction fails under severe feature turnover in COVID-19 supply chain tasks.
problem Dealing with distribution shift in conformal prediction models.
method Using COVID-19 as a natural experiment across 8 supply chain tasks, analyzing SHAP explanations.
result Coverage drops vary widely (0% to 86.7%) and correlate with single-feature dependence.
New risk decompositions clarify domain adaptation issues.
problem Domain adaptation challenges with different training and test distributions.
method Representation Bayesian Risk Decompositions, hybrid argument.
result Clarifies factors (2) and (3) as reasons for generalization failure.
This work improves neural network trustworthiness through uncertainty estimation.
problem Overconfident neural networks lead to poor performance under distribution shifts.
method Develops a general uncertainty framework for neural networks, including classification with rejection.
result Improves model trustworthiness and robustness in decision-making tasks.
SHAP explains boosted trees with additively modeled features.
problem Explaining predictions of boosted trees models with additively modeled features.
method SHAP values for additively modeled features in boosted trees models.
result SHAP dependence plot matches partial dependence plot for additively modeled features.
WassersteinGrad improves weather forecasting explanations by addressing geometric misalignment issues.
problem Improving explainability of autoregressive neural predictions on dynamic physical fields.
method WassersteinGrad, a geometric consensus method for averaged perturbed attribution maps.
result WassersteinGrad provides more accurate explanations for weather forecasting models.
GraphNorm accelerates GNN training by adapting InstanceNorm, improving convergence and generalization.
problem Improving convergence and generalization of Graph Neural Networks (GNNs).
method Adapting InstanceNorm to GNNs, proposing GraphNorm with a learnable shift.
result GNNs with GraphNorm converge faster and achieve better performance on benchmarks.
Machine learning detects regime shifts in online game-experiments with high accuracy.
problem Detecting regime shifts in online social systems.
method Gradient-boosted decision trees with memory-retaining features.
result Significantly outperforms standard early warning indicators.
Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing step ---adding a constant shift to the input data--- to show that a transformatio…
ISL improves causal structure learning with invariant structures across different environments.
problem Improving causal structure discovery for better generalization and explainability.
method ISL splits data into environments, learns invariant structures, and selects optimal classifiers based on graph structures.
result ISL accurately discovers causal structures and outperforms alternative methods on synthetic and real-world datasets.
New research shows LLMs can't be explained by statistical generalization alone.
problem Understanding why large language models (LLMs) perform well despite statistical generalization limitations.
method Examined the non-identifiability of AR probabilistic models and their implications for LLMs.
result Non-identifiability of LLMs leads to different behaviors and requires a separate theoretical explanation.
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…
The original research question here is given by marketers in general, i.e., how to explain the changes in the desired timescale of the market. Tangled String, a sequence visualization tool based on the metaphor where contexts in a sequence are compared to tangled pills in a string, is here extended and diverted to dete…
We introduce a notion of Ricci flow in generalized geometry, extending a previous definition by Gualtieri on exact Courant algebroids. Special stationary points of the flow are given by solutions to first-order differential equations, the Killing spinor equations, which encompass special holonomy metrics with solutions…
The paper addresses adversarial robustness in in-context learning models.
problem Adversarial distribution shifts threaten the reliability of in-context learning models.
method A distributionally robust meta-learning framework is introduced to provide worst-case performance guarantees under Wasserstein-based distribution shifts.
result Model robustness scales with the square root of its capacity and is penalized by the square of the perturbation magnitude.
New framework explains leading digit patterns without probabilistic assumptions.
problem Explaining leading digit distributions without relying on probabilistic models.
method Shift-invariant functional equation and affine-plus-periodic formulas.
result Unified mathematical foundation for understanding digit distributions.
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.
New method explains ML performance gaps without causal knowledge.
problem Understanding why ML algorithms perform differently across domains.
method Nonparametric hierarchical decomposition framework.
result Detailed variable-level explanations for performance gaps.
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.
TabPFN model outperforms previous methods on tabular data.
problem Improving performance on tabular data regression and classification.
method Transformer-based deep learning model for approximate Bayesian inference.
result TabPFN outperforms previous methods on datasets with up to 10,000 samples.
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.
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.
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…
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.
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.