A framework generates diverse counterfactual explanations for machine learning models.
problem Creating understandable explanations for machine learning predictions.
method Framework based on determinantal point processes for generating and evaluating diverse counterfactuals.
result Framework generates diverse counterfactuals that approximate local decision boundaries better than prior approaches.
Efficiently finds diverse coherent counterfactual explanations.
problem Finding coherent counterfactual explanations for complex data.
method Mixed integer programming with mixed polytope constraints.
result Efficiently generates diverse coherent counterfactual explanations.
δ-CLUE generates diverse explanations for model uncertainty.
problem Lack of constraints in generating explanations for uncertainty estimates.
method Augmenting CLUE approach to provide a set of plausible explanations.
result Returns a set of diverse inputs that yield confident predictions.
New methods improve uncertainty explanations for models.
problem Improving interpretation of uncertainty estimates from probabilistic models.
method Developed new methods to generate diverse and global explanations for uncertain model predictions.
result Generated diverse and global explanations for uncertain model predictions, addressing previous limitations.
Proposes MOC method for better counterfactual explanations in ML models.
problem Difficulties in balancing multiple objectives for counterfactual explanations.
method Translates counterfactual search into a multi-objective optimization problem.
result Returns diverse counterfactuals with different trade-offs and maintains feature diversity.
New method uses SHapley Additive Explanations to identify anomaly detectors with complementary behaviors.
problem Challenges in unsupervised anomaly detection due to diverse data distributions and lack of labels.
method Characterize anomaly detectors using SHapley Additive Explanations to measure feature importance and similarity.
result Detectors with similar explanations produce correlated anomaly scores, while those with divergent explanations are complementary.
The paper proposes a method to generate diverse counterfactual explanations for anomaly detection in time series data.
problem Lack of helpful explanations for anomaly detection models in time series data.
method Model-agnostic algorithm that generates diverse counterfactual examples for anomaly detection models.
result The method produces counterfactual examples that are not considered anomalous by the detection model and satisfy validity, plausibility, and closeness criteria.
Bayesian framework explains diverse explanatory values.
problem Understanding and predicting human preferences for explanations.
method Developed a Bayesian account to integrate various explanatory values.
result Core values from psychology, statistics, and philosophy emerge from a common framework.
LIMEtree offers faithful explanations for multiple classes in predictive models.
problem Generating explanations for several classes can be difficult due to conflicting evidence.
method LIMEtree uses multi-output regression trees for consistent and faithful explanations of multiple classes.
result LIMEtree provides diverse explanation types and outperforms LIME in evaluations.
The paper introduces a method to assess the reliability of model explanations.
problem Assessing the quality and reliability of model explanations.
method An Ordinal Consensus Approach using diverse bootstrapped surrogate explainers.
result Uncertainty estimates offer actionable insights beyond standard surrogate explainers.
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…
WISCA generates consensus explanations from conflicting model-agnostic interpretability methods.
problem Conflicting explanations from diverse interpretability algorithms.
method WISCA integrates class probability and normalized attributions to generate consistent explanations.
result WISCA consistently aligns with the most reliable individual method, improving explanation reliability.
TED framework teaches AI to explain decisions, improving accuracy.
problem Providing understandable explanations for AI predictions in high-stakes applications.
method Augmenting training data with explanations from domain users, using embeddings and multi-task learning.
result AI models can be taught to provide meaningful explanations, sometimes improving accuracy.
New algorithm generates counterfactual explanations for diverse models without restrictions.
problem Supporting consequential decisions with understandable explanations for predictive models.
method Solves satisfiability problems using logic formulae for model-agnostic, diverse explanations.
result Generates diverse, plausible counterfactuals at provably optimal distances.
Toolkit and taxonomy for diverse AI explainability methods.
problem Diverse stakeholder needs for AI explanations.
method Open-source software toolkit with eight explainability methods and evaluation metrics.
result Taxonomy helps navigate explanation methods.
Method explains anomaly detection by generating normal modifications.
problem Complexity of deep learning methods in anomaly detection.
method Generates multiple alternative modifications for anomalies.
result High-quality semantic explanations provided for anomaly detection.
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.
GANchors generates realistic image perturbations for better classifier explanations.
problem Improving the trustworthiness of image classification explanations.
method Using GANs to optimize a lower-dimensional latent space for realistic perturbation distributions.
result Generated images are more likely to be from the original training set, leading to more precise explanations.
Extends local attributions to Bayesian Neural Networks for improved explanations.
problem Lack of explanations for Bayesian Neural Networks' predictions.
method Extend local attributions to a probabilistic explanation distribution of BNNs.
result Enriches standard explanations with uncertainty information and visualizes explanation stability.
GIG improves IG to explain diverse ML functions.
problem Explain diverse ML functions effectively.
method Generalized Integrated Gradients (GIG) method.
result GIG is the only correct method under reasonable axioms.
Paper introduces Native Guide for generating time series counterfactual explanations.
problem Lack of explainability for time series data in AI systems.
method Model-agnostic, instance-based counterfactual generation for time series classification.
result Native Guide produces better counterfactual explanations than benchmarks.
Proposes simplified SHAP for faster black-box model explanations.
problem Computational expense of SHAP for models with many features.
method Ensemble of random SHAPs with feature selection and point generation.
result Efficiency and properties demonstrated through numerical experiments.
MACEM generates contrastive explanations for any classification model.
problem Generating meaningful explanations for non-differentiable models.
method Model Agnostic Contrastive Explanations Method (MACEM) for any classification model.
result MACEM generates contrastive explanations for models like random forests and boosted trees.
Multi-SpaCE generates valid counterfactual explanations for multivariate time series data.
problem Lack of transparency in deep learning models for multivariate time series data.
method Multi-objective counterfactual explanation method using NSGA-II for multivariate time series data.
result Ensures perfect validity and superior performance compared to existing methods.
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…
New method explains deep model decisions by adding latent features.
problem Limitations of existing local explanation methods for deep models.
method Leveraging latent features for contrastive local explanations.
result Quantitatively superior explanations on diverse datasets.
We introduce a method to learn a hierarchy of successively more abstract representations of complex data based on optimizing an information-theoretic objective. Intuitively, the optimization searches for a set of latent factors that best explain the correlations in the data as measured by multivariate mutual informatio…
The paper tackles strategic behavior in decision-making with counterfactual explanations.
problem Finding optimal counterfactual explanations and policies in a strategic setting.
method NP-hard problem, greedy algorithm, submodularity, randomized algorithm, matroid constraint.
result Optimal counterfactual explanations and policies increase utility.
XAI methods fail to explain ML models reliably.
problem Current XAI methods fail to provide reliable explanations for ML models.
method Formally define problems and design methods accordingly.
result Diverse notions of explanation correctness and metrics needed.
Interactive explanations improve machine learning transparency.
problem Transparency of machine learning predictions for diverse stakeholders.
method Personalized counterfactual explanations and follow-up questions.
result Improved understanding of black-box systems through interactive explanations.
Diversity or complementarity of experts in ensemble pattern recognition and information processing systems is widely-observed by researchers to be crucial for achieving performance improvement upon fusion. Understanding this link between ensemble diversity and fusion performance is thus an important research question. …
A new framework quantifies how model explanations influence each other.
problem Understanding how different model explanations interact and influence each other.
method Introducing the metagame, a conceptual framework for measuring second-order interaction effects of model explanations using Shapley values.
result Meta-attributions provide directional insights into how feature interactions influence model explanations.
Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization. However, recent studies have noted the occurrence of bias (under- or over-representation of a certain gender or race) in such data summarization methods. In this paper we initiate a s…
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.
Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on explanations for black-box models has produced tools (e.g. LIME) to show the im…
AI aids in mathematics research and problem-solving.
problem Complex mathematical problems and discoveries.
method Explains AI principles and diverse applications in math.
result AI assists in discovering patterns, proving theorems, and challenging conjectures.
DEMUD-VIS detects novel image content and explains it visually.
problem Detecting and explaining novel image content in large datasets.
method Uses CNN for feature extraction, reconstruction error for novelty detection, and up-convolutional networks for image reconstruction.
result Demonstrates visual explanations of novel image content on diverse datasets.
Deep ensembles improve model accuracy and robustness, but their theoretical underpinnings are not fully understood.
problem Understanding why deep ensembles work well in practice despite theoretical limitations.
method Investigating the loss landscape of neural networks and exploring the diversity of functions in function space.
result Random initializations explore diverse modes in function space, while ensembles along an optimization trajectory cluster within a single mode.
Transformers prefer simpler explanations in hierarchical tasks.
problem Navigating tasks with varying complexity levels.
method Well-controlled testbeds based on Markov chains and linear regression.
result Transformers favor the least complex sufficient explanation when presented with simpler data.
Study links neural network inductive bias, feature learning, and generalization on Boolean functions.
problem Understanding how neural networks learn and generalize on Boolean data.
method End-to-end analysis of depth-2 discrete fully connected networks and DNF formulas, using Monte Carlo learning.
result Predictable training dynamics and interpretable features emerge, linking inductive bias and generalization.
Unified causal models are formed from fragmented data sets.
problem Combining fragmented data sets to form a unified causal explanation is challenging.
method Using conditional independence properties of marginal datasets to reduce the number of possible models.
result Reduces the number of possible models to a unique one in some cases.
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.
New method interprets complex models for music and urban simulations.
problem Difficulties in understanding deep neural network predictions.
method Uses generative models to improve explanation clarity.
result Flexibility demonstrated across diverse modalities (music, urban simulations).
Proposes sparse local and regional counterfactual rules for robust recourses.
problem Challenges in counterfactual explanations, especially stability, synthesis, and implementation.
method Probabilistic framework using Random Forest to derive sparse local and regional counterfactual rules.
result Effective recourses derived from high-density regions, providing sparse and robust counterfactual rules.
Synthesizes computational approaches to understand neural timescales.
problem Varying definitions and measurements of neural timescales across studies.
method Reviews data analysis methods, biophysical models, and machine learning models.
result Complements experimental studies with a holistic view of neural timescales.
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…
Learning by children and animals occurs effortlessly and largely without obvious supervision. Successes in automating supervised learning have not translated to the more ambiguous realm of unsupervised learning where goals and labels are not provided. Barlow (1961) suggested that the signal that brains leverage for uns…
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.