Mathematical study shows post-hoc explanations are better than attention weights alone.
problem Understanding the internal behavior of attention-based models.
method Mathematical analysis of a simple attention-based architecture.
result Post-hoc explanations provide more useful insights than attention weights alone.
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
problem CNNs lack accurate data representation in their built-in prototypes.
method Introduces k-means-based post-hoc explanations for CNNs, leveraging spatial consistency of convolutional receptive fields.
result Using shallower, less compressed feature activations improves semantic fidelity at the cost of slight predictive performance.
TaylorPODA uses Taylor expansions to improve feature attributions for opaque models.
problem Lack of systematic framework for quantifying feature contributions in opaque models.
method Taylor expansion framework with postulates (precision, federation, zero-discrepancy, adaptation).
result TaylorPODA achieves competitive results and provides principled explanations.
Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the assumptions they make about the data and the classifier make them unreliable in many contexts. In this paper, we discuss three desirable pro…
EAGLE improves reproducibility and stability of model explanations.
problem Creating reliable explanations for opaque machine learning models.
method Formulates perturbation selection as an information-theoretic active learning problem.
result EAGLE learns a linear surrogate model with feature importance scores and uncertainty estimates.
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be unpredictable. Our method, ExpO, is a hybridization of these approaches that regu…
As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for explaining these black boxes in an interpretable manner. Such explanations are being leveraged by domain experts to diagnose systematic error…
Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a result of some artifacts learned by the model instead of actual knowledge from the data. This paper f…
PACE explains ViTs by modeling patch-level concept distributions, surpassing existing methods.
problem Lack of trustworthy post-hoc explanations for Vision Transformers (ViTs)
method Variational Bayesian explanation framework (PACE)
result PACE surpasses state-of-the-art methods in meeting desiderata for ViT explanations.
ID-ExpO fine-tunes neural networks for more faithful explanations.
problem Improving the faithfulness of explanations for complex machine learning models.
method Differentiable insertion/deletion metric-aware regularizers for optimization.
result Fine-tuned predictors produce more faithful explanations.
New methods identify concepts in trained embeddings reliably without human labels.
problem Identifying interpretable concepts in trained embedding spaces without human labels.
method Explicitly connecting concept discovery to PCA and ICA, proposing novel approaches for dependent concepts.
result Proven methods outperform competitors on a variety of experiments, achieving up to 29% better alignment with ground truth.
Attack reveals model details from counterfactual explanations.
problem Extracting model details from counterfactual explanations.
method Adversary uses counterfactual explanations to build high-fidelity model.
result High-fidelity and high-accuracy model extraction possible.
LLMs can help explain credit risk models but not autonomously.
problem Leveraging LLMs for post-hoc explainability in credit risk models.
method Comparison of LLM outputs with SHAP and coefficient-based attributions on three LMs.
result LLMs reliably preserve feature-importance rankings but poorly align with autonomous explanations.
S-LIME stabilizes LIME for more reliable model explanations.
problem Instability of post hoc explanation methods like LIME.
method Uses hypothesis testing based on central limit theorem to stabilize explanations.
result Demonstrates effectiveness of S-LIME on simulated and real-world data.
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.
Study proposes explainable analytics for manufacturing process planning.
problem Improving data-driven decision-making in manufacturing.
method Combines process mining, machine learning, and XAI. Uses deep learning for prediction and Shapley values/ICE plots for explanations.
result Enhanced decision-making capabilities through local post-hoc explanations.
Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This motivates the development of models that are equally accurate but can be also e…
Explains agent behavior through intended outcomes in reinforcement learning.
problem Proving impossibility of general post-hoc explanations in reinforcement learning.
method Derives local explanations based on intention for Q-function approximations, proving consistency with learned Q-values.
result Demonstrates the necessity of collecting information during training for accurate explanations.
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.
XCM improves MTS classification with explainable deep learning.
problem Lack of explainable deep learning models for MTS classification.
method XCM is a compact CNN that extracts variable and timestamp information directly from input data.
result XCM outperforms state-of-the-art MTS classifiers on large and small datasets.
Study robustness of global feature effect explanations in machine learning models.
problem Vulnerability of global feature effect explanations to data and model perturbations.
method Theoretical bounds and experimental evaluation of partial dependence plots and accumulated local effects.
result Quantifies the gap between best and worst-case scenarios of misinterpreting machine learning predictions globally.
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their explanation quality. We propose an alternative to these approaches by directly r…
Study shows more data improves model explanations, aiding reliable knowledge extraction.
problem Challenges in deriving reliable knowledge from machine learning models due to the Rashōmon effect.
method Examined the influence of sample size on explanations from models in a Rashōmon set using SHAP.
result Explanations from <128 samples are highly variable, but agreement improves with more data.
Develops causal explanations for black-box classifiers.
problem Creating understandable explanations for complex models.
method Generative model with information-theoretic measures of causal influence.
result Learned latent factors influence classifier outputs.
New method quantifies intrinsic causal contributions in neural networks.
problem Measuring the causal influence of input features in deep neural networks.
method Proposes an identifiable generative post-hoc framework to quantify intrinsic causal contributions (ICC) as structural causal models.
result ICC generates more intuitive and reliable explanations compared to existing global explanation techniques.
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations shoul…
CTE improves explanation estimation with less data and faster computation.
problem Inefficient and inaccurate explanation estimation in machine learning models.
method Distribution compression through kernel thinning to reduce sample size.
result CTE significantly improves accuracy and stability of explanation estimation.
PiNets provide faithful explanations for neural networks.
problem Lack of true explanations for neural network predictions.
method Pointwise-interpretable Networks (PiNets) that form linear models instance-wise.
result PiNets offer explanations that are meaningful, aligned, robust, and sufficient.
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.
Bayes-TrEx finds in-distribution examples for model inspection.
problem Challenges in interpreting neural networks, especially high-confidence failures and ambiguous classifications.
method Bayesian sampling approach to find in-distribution examples with specified prediction confidence.
result Bayes-TrEx enables more flexible holistic model analysis than just inspecting the test set.
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.
Enhances counterfactual explanations with more valid and informative saliency maps.
problem Lack of valid counterfactual explanations in existing models.
method Introduces a modified approach to CELS model by removing mask normalization.
result Demonstrates higher validity and more informative counterfactual explanations.
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.
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.
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.
CUBE explains models by balanced experiments and contrasts.
problem Post-hoc explanation of trained predictive models.
method Design-based framework using balanced low-high probes.
result Reveals dominant learned effect structure and clarifies query efficiency.
Proposes a method for multilevel explanations of black-box models.
problem Need for explanations at intermediate or group levels, especially for GDPR compliance.
method Meta-method that builds a multilevel explanation tree using local explainability methods.
result Effective multilevel explanations for groups of data points, including novel test points.
Paper proposes a method to make image model explanations robust to distortions.
problem Ensuring robustness of explanations for images under distortions.
method Embedding perceptual distances in surrogate explainers to evaluate and improve robustness.
result Surrogate explanations become more coherent and robust to distortions.
Proposes an efficient method for ordered counterfactual explanations.
problem Insufficient explanation of perturbation vectors for executing actions.
method Mixed-Integer Linear Optimization (MILP) approach for evaluating and extracting optimal pairs of actions and orders.
result Demonstrated effectiveness of the proposed method on real datasets.
Bayesian framework improves reliability and consistency of model explanations.
problem Inconsistent and unreliable explanations from state-of-the-art methods.
method Developed a novel Bayesian framework for generating local explanations with associated uncertainty.
result Generated explanations are consistent, stable, and provide credible intervals for feature importances.
Improves local model explanations using GANs and Linear Model Trees.
problem Need for accurate and intuitive explanations of complex machine learning models.
method Generative Adversarial Network (GAN) for synthetic data generation and Linear Model Trees for surrogate model training.
result Significantly improved local model explanations with contextual information.
The paper detects and identifies bias in data using a counterfactual approach.
problem Detecting and identifying bias in data, especially in medical image classification.
method A global explanation framework using the counterfactual approach to identify bias causing artifacts.
result Black frames significantly influence Convolutional Neural Network's prediction, changing benign to malignant.
The paper proposes new interpretability paradigms to improve model faithfulness.
problem Improving the accuracy of explanations for complex models.
method Examining and evolving existing paradigms, proposing new models.
result Three new paradigms for interpretability are presented.
In this paper, we study two challenging problems in explainable AI (XAI) and data clustering. The first is how to directly design a neural network with inherent interpretability, rather than giving post-hoc explanations of a black-box model. The second is implementing discrete k-means with a differentiable neural net…
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.
Unified feature importance for machine learning models tackles sufficiency and necessity limitations.
problem Insufficient and incomplete explanations of machine learning models.
method Formalized sufficiency and necessity notions, proposing a unified importance measure.
result Unified importance measure detects features missed by sufficiency and necessity alone.
Instantly interprets black-box models using additive models.
problem Efficiency and representation power of SHAP explanations.
method Variational perspective linking GAM models and SHAP explanations; InstaSHAP method.
result Automatic computation of Shapley values in a single forward pass.
XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers. Overall, XDeep takes a trained deep neural network (DNN) as the input, and generates relevant interpretations as the output with the post-hoc manner. From the functionality perspective, XDeep integrates a w…