Improved local explainer aggregation for interpretable machine learning models.
problem Improving the interpretability of black box machine learning models.
method Non-convex optimization and integer optimization framework for local explainer aggregation.
result Our method outperforms existing methods in terms of coverage and fidelity, particularly in multi-class settings.
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.
The paper connects machine learning interpretability with learning theory.
problem Performance and explanation generalization in local machine learning models.
method Theoretical analysis and empirical validation of local approximation explanations.
result Theoretical bounds on test-time accuracy and explanation generalization.
Local surrogate model improves time series forecasts and provides interpretable explanations.
problem Improving time series forecasting accuracy while maintaining interpretability.
method A local surrogate model is used to correct the base model's predictions, making the corrections interpretable by re-fitting the base model to the error-predicted data.
result The method can discover and explain underlying patterns in the data, improving both accuracy and interpretability.
Enhances local explainability and trust scores using RF proximities.
problem Improving local explainability and trust in random forest models.
method Rewriting RF predictions as weighted sums of training targets using proximities.
result Proximities provide a novel method to assess model predictions' correctness.
Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are model-agnostic and are post-hoc (i.e., can be retrofitted). The Local Interpretable Model-agnostic …
Local decision boundary approximation improves model explanations for complex models.
problem Challenges in explaining complex, opaque machine learning models.
method Train a variational autoencoder to learn a latent space and map it to meaningful attributes. Use these attributes to approximate the local decision boundary and explain model predictions.
result Can recover latent attributes that determine class decisions in a new benchmark data set.
A new method improves LIME for better model explanation.
problem Current LIME explanations are not faithful and weak in understanding.
method Proposes a novel Modified Perturbed Sampling (MPS) for LIME.
result MPS-LIME achieves better performance in understandability, fidelity, and efficiency.
SMILE improves explainability of machine learning models.
problem Difficulty in understanding and trusting the conclusions of black-box machine learning models.
method Statistical Model-agnostic Interpretability with Local Explanations (SMILE).
result SMILE makes machine learning models more interpretable.
As we rely more and more on machine learning models for real-life decision-making, being able to understand and trust the predictions becomes ever more important. Local explainer models have recently been introduced to explain the predictions of complex machine learning models at the instance level. In this paper, we p…
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an interpretable model. We demonstrate the flexibility of CLE by explaining different models…
Survey of Locally Linear Embedding and its variants.
problem Representing high-dimensional data in a lower-dimensional space while preserving local structure.
method Explains various LLE and variant methods, including kernel LLE, inverse LLE, feature fusion, out-of-sample embedding, incremental LLE, landmark LLE, supervised LLE, robust LLE, fusion with other methods, and weighted LLE.
result Comprehensive overview of LLE and its variants.
We introduce a method, KL-LIME, for explaining predictions of Bayesian predictive models by projecting the information in the predictive distribution locally to a simpler, interpretable explanation model. The proposed approach combines the recent Local Interpretable Model-agnostic Explanations (LIME) method with ideas …
A new framework explains GNN predictions by simulating graph structure and feature changes.
problem Lack of transparency in GNN predictions hinders understanding.
method TraP2 framework using a three-layer architecture: Translation, Perturbation, and Paraphrase layers.
result TraP2 achieves 10.2% higher explanation accuracy than state-of-the-art methods.
As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated with model interpretability. Many machine learning algorithms induce models diff…
This paper enhances credit risk management using explainable AI techniques.
problem Lack of transparency and explainability in AI models for credit risk management.
method Implement LIME and SHAP for explaining ML-based credit scoring models.
result Demonstrates practical challenges and solutions for XAI methods in finance.
CoxSE combines deep learning with self-explaining neural networks for survival analysis.
problem Improving predictive power of Cox Proportional Hazards model while maintaining explainability.
method Proposes CoxSE, a locally explainable Cox proportional hazards model using SENN, and CoxSENAM, a hybrid model with NAM.
result CoxSE provides more stable and consistent explanations while maintaining predictive power.
Unified view of improving tree model interpretability and debiasing feature importance.
problem Improving interpretability and debiasing feature importance in tree-based models.
method Demonstrates a common thread among bias correction methods and local explanations for trees.
result Points out a bias in explainable AI for trees algorithms due to inbag data inclusion.
SurvLIME explains survival models by approximating them with Cox models.
problem Explaining complex survival models in machine learning.
method Applies Cox proportional hazards model to approximate survival model locally.
result Demonstrates efficiency through numerical experiments.
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
problem Local feature attributions become obsolete in evolving data streams.
method CDLEEDS, a flexible framework for detecting local change and concept drift.
result CDLEEDS reliably detects both local and global concept drift.
SyMPLER improves time series forecasting in nonstationary environments with explainable models.
problem Nonstationary time series forecasting with limited interpretability.
method Dynamic piecewise-linear approximations based on Statistical Learning Theory generalization bounds.
result SyMPLER achieves comparable performance to black-box and explainable models while maintaining interpretability.
New method explains survival analysis models using median-SHAP.
problem Need for explainable AI in medical applications, especially for survival analysis.
method Introduces median-SHAP for explaining survival analysis models.
result Conventionally used mean anchor point can lead to misleading interpretations; median-SHAP provides a better approach.
Normal forms for Q-structures on graded manifolds explained.
problem Understanding structures of Q-manifolds on graded manifolds.
method Local and global normal forms results for Q-structures.
result Structures are concentrated along the zero-locus of curvatures.
P-SE explains model decisions with minimal feature subsets and fast estimators.
problem Explain model decisions in regression and classification.
method Probabilistic Sufficient Explanations (P-SE) with random Forests for conditional probability estimation.
result Consistent and efficient explanations for regression and classification models.
GraphHull models networks with clear multi-scale explanations of community structure.
problem Lack of self-explainable models in graph machine learning.
method Two-level convex hulls with global archetypes and local prototypes.
result GraphHull models networks with clear multi-scale explanations.
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.
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.
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the model's behavior. LIME develops multiple interpretable models, each approximat…
Explains model structures for higher orbifolds and applies them to quantum cohomology.
problem Understanding quantum cohomology of higher orbifolds.
method Develops model structures on higher orbifolds and applies them to quantum cohomology.
result Model structures provide insights into quantum cohomology of higher orbifolds.
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.
Proposes a framework to explain complex global forecasting models.
problem Lack of interpretability in global forecasting models reduces stakeholder trust.
method Trains simpler univariate surrogate models on local forecasts of global models.
result Shows improved local model-agnostic interpretability of global forecasting models.
Machine learning is used more and more often for sensitive applications, sometimes replacing humans in critical decision-making processes. As such, interpretability of these algorithms is a pressing need. One popular algorithm to provide interpretability is LIME (Local Interpretable Model-Agnostic Explanation). In this…
Study compares and contrasts various ML explanation methods, highlighting their disagreements and similarities.
problem Understanding and quantifying the differences between various machine learning explanation methods.
method Synthesized and visualized various explanation methods for global and local aspects of ML models.
result There is substantial agreement on the top features but less on specific rankings, and tree interpreter is comparable to SHAP for feature effects.
In this paper we discuss the twistor equation in Lorentzian spin geometry. In particular, we explain the local conformal structure of Lorentzian manifolds, which admit twistor spinors inducing lightlike Dirac currents. Furthermore, we derive all local geometries with singularity free twistor spinors that occur up to di…
Study proposes a novel local explanation method for deep learning classifiers in process mining.
problem Lack of interpretability in deep learning models for process mining.
method Defines local regions using latent space representations and visualizes explanations.
result Deep learning classifier achieves high performance and local explanations increase user trust.
In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make these complex models explainable, we present DeepSHAP for mixed model types, a framework for layer wise propagation of Shapley values that bu…
Meta-learning framework improves explainability of GNNs.
problem Improving explainability of graph neural networks.
method Meta-learning framework to steer GNN training towards interpretable minima.
result Models are easier to explain by different algorithms without sacrificing accuracy.
Method extracts time-localized clusters to explain deep learning models in ECG analysis.
problem Limited understanding of deep learning models in ECG analysis.
method Extracts time-localized clusters from model's internal representations.
result Enhances trust in AI-driven diagnostics and reveals clinically relevant patterns.
Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results. Explainability is not only a gateway between AI and society but also a powerful tool t…
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.
SX-GeoTree improves spatially coherent explanations in geospatial regression trees.
problem Capturing spatial dependence and producing robust explanations in tabular prediction models.
method Integrates three objectives: impurity reduction, spatial residual control, and explanation robustness via modularity maximization on a consensus similarity network.
result Improves residual spatial evenness and doubles attribution consensus (modularity: Fujian 0.19 vs 0.09; Seattle 0.10 vs 0.05).
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.
We explain the meaning of local symmetries in physics.
problem Understanding the meaning of local symmetries in physics.
method We argue that general covariance and gauge principles are principles of epistemic access to physical laws, leading to ontological insights.
result Relationality is a core notion in gauge field theory, encoded by local symmetries.
Survey of Laplacian-based methods for data dimensionality reduction and embedding.
problem Efficiently reducing high-dimensional data to lower dimensions while preserving important features and structures.
method Laplacian-based methods including spectral clustering, Laplacian eigenmap, locality preserving projection, graph embedding, and diffusion map.
result Comprehensive overview of various optimization variants and applications of Laplacian-based techniques.
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on two definitions of interpretability that have been introduced in the machine learn…
Existing works on "black-box" model interpretation use local-linear approximations to explain the predictions made for each data instance in terms of the importance assigned to the different features for arriving at the prediction. These works provide instancewise explanations and thus give a local view of the model. T…
Survey reviews explainability in AI for healthcare, emphasizing trust and transparency.
problem Lack of transparency hinders AI adoption in healthcare.
method Comprehensive literature review to guide explainable AI design.
result Quantitative evaluation metrics are needed for some explainability properties.
Posterior collapse in Variational Autoencoders (VAEs) arises when the variational posterior distribution closely matches the prior for a subset of latent variables. This paper presents a simple and intuitive explanation for posterior collapse through the analysis of linear VAEs and their direct correspondence with Prob…