Current XAI research lacks solid foundations and clear goals.
problem Inadequate conceptual, ethical, and methodological foundations in XAI research.
method Discussion of misconceptions and suggestions for improvement.
result Current XAI research needs to address conceptual, ethical, and methodological issues.
A new method accounts for predictor dependencies in XAI feature rankings.
problem Assumption of predictor independence in XAI methods leads to unreliable feature rankings.
method Proposes a proxy method to modify XAI outcomes considering predictor dependencies.
result Allows more accurate feature ranking in models with correlated predictors.
XAI methods often misattribute importance to suppressor variables, limiting their reliability.
problem XAI methods lack theoretical and empirical evidence for the correctness of their explanations.
method Analytical expressions for XAI methods on a simple binary classification problem.
result XAI methods will often attribute non-zero importance to non-class-related suppressor features.
AEC method improves XAI for models with collinear features.
problem Collinearity issues in machine learning models.
method Divides multivariate models into univariate models to examine feature effects.
result AEC method is more robust and stable against collinearity.
The paper explores AI in finance, focusing on XAI's role in enhancing interpretability and trust.
problem The need for AI in finance and the importance of XAI for better decision-making.
method Tracing AI's evolution in finance, highlighting XAI's role, and demonstrating through simulations.
result XAI enhances trust in AI systems, leading to more responsible decision-making.
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.
Study reveals XAI methods fail in neuroimaging, suggesting domain-specific adaptation.
problem Systematic failures of XAI methods in neuroimaging applications.
method Systematic comparison of XAI methods on 45,000 structural brain MRIs using a novel validation framework.
result Two widely used XAI methods (GradCAM and Layer-wise Relevance Propagation) fail to accurately explain neuroimaging data.
xAI-GAN improves GANs by providing richer feedback, enhancing image quality.
problem Challenges in GAN training, especially resource-intensive and data-intensive.
method Integrates xAI systems to provide richer corrective feedback from discriminators to generators.
result Improves image quality by up to 23.18% on MNIST and FMNIST datasets.
Counterfactuals help compare different scenarios in CI and XAI.
problem Comparing how counterfactuals are used in causal inference and explainable AI.
method Formal definition and comparison of counterfactuals in CI and XAI.
result Identified opportunities for cross-fertilization between CI and XAI.
PatternLocal improves XAI for non-linear models by suppressing suppressor variables.
problem Suppressor variables cause false-positive feature attributions in non-linear models.
method PatternLocal uses locally linear surrogate models and transforms weights into a generative representation.
result PatternLocal reduces false-positive attributions and provides more reliable explanations.
This review explores XAI in finance, highlighting common techniques and areas needing improvement.
problem Balancing accuracy and transparency in financial AI models.
method Bibliometric and content analysis of XAI applications in finance.
result Post-hoc interpretability techniques are most used in financial XAI.
This review explores XAI methods and multicollinearity issues.
problem Multicollinearity affects the interpretability of AI models.
method A review of current XAI approaches and their limitations.
result Current XAI methods struggle with multicollinearity.
Paper defines XAI concepts using category theory.
problem Lack of precise mathematical definitions for XAI.
method Uses Category theory to define XAI concepts rigorously.
result Establishes a theoretical foundation for XAI.
This work develops a high precision fault diagnosis classifier using XAI insights.
problem Fault diagnosis of steel plates in manufacturing industry.
method Incorporation of XAI insights into Data Science process using SMOTE and medoids.
result 10 fold cross validated performance of 94% achieved.
This review clarifies XAI for regression models and establishes new theoretical insights.
problem Lack of XAI techniques for regression models, especially in safety-critical applications.
method Clarifies conceptual differences, establishes theoretical insights, provides demonstrations, discusses challenges.
result Novel theoretical insights and demonstrations of XAI for regression models.
XAI identifies key time steps for early crop classification.
problem Early crop classification with high accuracy and timeliness.
method Training a baseline model with LRP to identify important time steps.
result Identified a 21st April 2019 to 9th August 2019 timeframe with 0.75% accuracy loss.
This paper explores good practices for AI explainability in finance.
problem Complex financial models lack transparency and interpretability.
method Exploring good practices for deploying explainability in AI-based financial systems.
result Developing effective XAI tools for the financial industry.
This paper catalogs R packages for explaining AI models.
problem Ensuring safe and effective functioning of predictive models.
method Taxonomy of model explanations and comparison of R packages.
result 27 R packages for XAI identified and compared.
Survey connects XAI and surrogate modeling for better understanding of complex systems.
problem Opaque surrogate models hide input-output relationships, hindering decision-making.
method Synthesizes XAI techniques with surrogate modeling workflows.
result Surrogate models can be made more interpretable using XAI methods.
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…
AutoML enhances credit decisions with XAI for better transparency.
problem Transparency in AI-driven financial decisions.
method Combining AutoML and XAI (SHAP) for credit scoring.
result Improved efficiency and accuracy in credit decisions with enhanced transparency.
The paper uses DNN for electricity price forecasting and XAI for understanding the factors.
problem Complex interactions and dependencies in electricity markets make it hard to understand price dynamics.
method Used DNN for forecasting and XAI (SHAP, Gradient, heatmaps) for understanding factors.
result Introduced novel concepts SSHAP values and SSHAP lines for enhanced representation of high-dimensional tabular models.
The paper uses XAI to predict RFQ fulfillment accuracy.
problem Improving accuracy in predicting RFQ fulfillment for less liquid asset classes.
method Advanced algorithms like Logistic Regression, Random Forest, XGBoost, and Bayesian Neural Tree.
result Improved accuracy in RFQ fill rate predictions.
This work explores how XAI methods can visualize the diversity of feature representations in Bayesian Neural Networks.
problem Explaining the diversity of feature representations learned by Bayesian Neural Networks.
method Application of global XAI methods to visualize and quantify the diversity of feature representations.
result The diversity of learned feature representations correlates with uncertainty estimates and network width.
Study examines XAI methods for ECG analysis to improve model transparency.
problem Lack of transparency in deep learning models for ECG analysis.
method Investigates post-hoc XAI methods for local and global perspectives, establishes sanity checks, and demonstrates knowledge discovery.
result Quantitative evidence supports expert rules for sensible attribution methods and demonstrates XAI's utility for knowledge discovery.
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.
MCD offers a complete model understanding for high-stake decisions.
problem Local model understanding in XAI methods is not sufficient for high-stake decisions.
method MCD extends concept-based methods to ensure global model understanding via multi-dimensional subspaces.
result MCD provides a complete model understanding, ensuring the model reasoning is related to the actual model.
Researchers use DL and XAI to evaluate climate downscaling models.
problem Evaluating complex DL models for climate downscaling.
method Intercompare DL models, expand standard evaluation methods with XAI.
result XAI techniques provide new evaluation dimensions and model insights.
This paper uses XAI techniques to explain meta-learning models.
problem Lack of understanding how meta-features contribute to model performance.
method XAI techniques applied to explain black-box surrogate models.
result Improved understanding of meta-features' importance and effect.
Survey on making reinforcement learning models more understandable.
problem Complex reinforcement learning models are hard to interpret.
method Classification and assessment of current XRL methods.
result Most XRL methods simplify complex models rather than designing simple ones.
Two XAI methods, SHAP and LIME, are discussed for tabular data models.
problem Making machine learning models transparent and trustworthy.
method SHAP and LIME methods for explaining model predictions.
result SHAP and LIME are model-dependent and sensitive to feature collinearity.
Machine learning (ML) is increasingly used to support decision-making in the healthcare sector. While ML approaches provide promising results with regard to their classification performance, most share a central limitation, namely their black-box character. Motivated by the interest to understand the functioning of ML …
PWSHAP provides targeted explanations for complex models.
problem Inability of black-box models to explain targeted effects in sensitive domains.
method Augments model with DAG, uses Shapley values for causal pathway identification.
result Establishes error bounds and demonstrates resolution, interpretability, and locality.
Study evaluates saliency maps on artificial data with different backgrounds.
problem Objective evaluation of saliency methods on artificial data with varying backgrounds.
method Developed a framework to generate artificial data with synthetic lesions and a known ground truth map, evaluated two data sets with different backgrounds (Perlin noise and 2D brain MRI slices).
result Heatmaps vary strongly between saliency methods and backgrounds.
XAI-Bench releases synthetic datasets for evaluating feature attribution methods.
problem Evaluating and comparing feature attribution methods is challenging.
method Released synthetic datasets and benchmarking library.
result Efficiently evaluates feature attribution methods across various metrics.
A new method for measuring conditional feature importance using generative models.
problem Challenges in evaluating feature importance given other feature values.
method Adversarial Random Forest (ARF) for generating on-manifold data points.
result cARFi method yields robust importance scores adaptable for various feature importance notions.
This research integrates attention into XAI frameworks for better model explanations.
problem Improving the interpretability of transformer models.
method Developed two novel explanation methods: Shapley value decomposition and token-level directional derivatives.
result Attention weights can be meaningfully incorporated into XAI frameworks, enhancing transformer explainability.
XAI methods struggle with identifying true predictors from suppressors in linear datasets.
problem XAI methods misidentify suppressor variables as important features.
method Carefully crafted linear ground-truth dataset to study suppressor variables; evaluated various XAI methods.
result Most XAI methods fail to distinguish true predictors from suppressors in linear settings.
CEILS generates feasible counterfactual explanations by considering causal impacts.
problem Current counterfactual explanations lack feasibility and causal impact consideration.
method CEILS integrates causal reasoning into existing counterfactuals generation algorithms.
result CEILS provides feasible recommendations to achieve desired outcomes.
Identifies key industrial sectors in S&P 500 states.
problem Understanding changing market conditions in financial markets.
method Clustering algorithm, XAI relevance scores, Bayesian change point analysis.
result Dominant sectors (energy and IT) determine market states.
Unified framework for linear attribution methods in deep learning.
problem Separate theoretical foundations of XAI attribution methods.
method GRALIS (Gradient-Riesz Averaged Locally-Integrated Shapley) framework.
result Unified representation theory for linear attribution methods.
ViTaX provides formal guarantees for targeted explanations in safety-critical systems.
problem Need trustworthy explanations for safety-critical deep neural networks.
method Formal reachability analysis for targeted, semifactual explanations.
result First method to provide formally guaranteed explanations of model resilience.
Paper combines multiple ETA models into a stacked ensemble for better ETA predictions.
problem Improving ETA predictions for taxi schedules and trips.
method Developed a two-level stacked ensemble model and applied XAI methods to explain it.
result The stacked ensemble model outperforms previous ETA approaches.
Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in the novel field of explainable artificial intelligence (XAI). In this…
There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, p…
Establishing unique identities for both humans and end systems has been an active research problem in the security community, giving rise to innovative machine learning-based authentication techniques. Although such techniques offer an automated method to establish identity, they have not been vetted against sophistica…
New AI technique explains neural net decisions over time.
problem Difficulty of explaining AI decisions in time series data.
method Proposes a novel XAI technique for deep learning methods.
result Preserves and exploits the natural time ordering of data.
New framework for contesting algorithmic decisions, not just explaining them.
problem Helping individuals review and correct erroneous algorithmic decisions.
method Operationalized contestability as a natural complement to explainable AI (XAI), identifying three types of evidence for reversal.
result Existing EU legislation already grants individuals legal rights to contest algorithmic decisions.