We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.
The study designs inherently interpretable machine learning models for high-risk sectors.
problem The need for transparent and explainable machine learning models in regulated industries.
method Qualitative template based on feature effects and model architecture constraints for assessing inherent interpretability.
result Demonstrates the design and evaluation of an interpretable ReLU DNN model for predicting credit default.
Integrating causal machine learning with inherently interpretable models for decision support.
problem Providing causal insights and decision support through machine learning models.
method Proposing an approach that integrates causal machine learning with inherently interpretable models.
result The proposed approach achieves competitive performance in prediction and what-if analysis while offering transparency on the system structure, causal relationships among variables, and functional forms connecting them.
Federated learning framework improves model generalization and privacy.
problem Communication overhead and statistical heterogeneity in FL.
method Prototypes and lightweight adapters for local model refinement.
result Improves classification accuracy over baseline algorithms.
Shallow trees in ensemble models make models more interpretable and sometimes better.
problem Lack of transparency in high-performing tree ensemble models.
method Developed an interpretation algorithm to convert tree ensembles into functional ANOVA representations. Proposed strategies to enhance interpretability.
result Shallow trees in ensemble models can lead to better generalization performance and improved interpretability.
NIMO combines interpretability with neural networks for clear feature effects.
problem Lack of interpretability in deep learning models.
method Combines neural networks with linear regression using adaptive ridge regression.
result NIMO provides faithful and intelligible feature effects while maintaining good predictive performance.
Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for explaining these black box models will alleviate some of these problems, but trying t…
NAMLSS models provide interpretable neural regression for location, scale, and shape.
problem Lack of interpretability in deep learning models for complex data distributions.
method Combines classical statistical methods with DNNs for distributional regression.
result Achieves visual interpretability and predictive power of deep learning models.
We propose to use boosted regression trees as a way to compute human-interpretable solutions to reinforcement learning problems. Boosting combines several regression trees to improve their accuracy without significantly reducing their inherent interpretability. Prior work has focused independently on reinforcement lear…
The paper improves decision tree stability for health care applications.
problem Stability of decision trees in health care applications.
method Introducing a new distance metric to determine tree stability and proposing a novel training methodology.
result On average, a 4.6% decrease in predictive power yields a 38% increase in model stability.
CoDA Nets improve interpretability in neural networks.
problem Improving interpretability in neural networks.
method Dynamic Alignment Units (DAUs) for input-dependent linear transformations.
result CoDA Nets achieve on par results with ResNet and VGG models on complex datasets.
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…
Unified approach to learn interpretable concepts from data.
problem Building interpretable machine learning models and highly-performing foundation models.
method Relating causal representation learning and foundation models, defining concepts and proving their recoverability.
result Provable recovery of human-interpretable concepts from diverse data.
This paper explores causal analysis in machine learning for better interpretability.
problem The lack of causality in traditional interpretable machine learning models.
method An overview of causal approaches for interpretable machine learning.
result Causal analysis improves the interpretability of machine learning models.
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…
Paper breaks down risk contribution into inherent and correlation risk components.
problem Understanding the sources of risk in portfolio contributions.
method Leave-one-out decomposition approach to separate inherent and correlation risk contributions.
result The decomposition reveals distinct contributions of position volatility and correlation to portfolio risk.
Develops an ordinal-similarity framework for scalable and interpretable representation alignment.
problem Measuring representation similarity in large datasets.
method Triplet and Quadruplet Similarity Indices.
result Demonstrates inherent interpretability, robustness to outliers, and computational efficiency.
The paper introduces metrics to objectively evaluate interpretability methods.
problem Lack of objective evaluation metrics for interpretability methods.
method Proposes a set of metrics to evaluate interpretability methods along simplicity and broadness.
result Validated metrics on different benchmark tasks and showed their utility in method selection.
Paper proposes a new method to evaluate AI model interpretability in bond default prediction.
problem Lack of standardized method to assess inherent interpretability of AI models.
method Uses LIME and SHAP to assess feature contributions in bond default prediction.
result Consistent results with intuitive understanding of model interpretability.
SurvFD and SurvSHAP-IQ provide interpretable survival models by analyzing feature interactions.
problem Non-additivity of hazard and survival functions limits standard additive explanation methods.
method SurvFD decomposes higher-order effects into time-dependent and time-independent components, extending Shapley interactions to time-indexed functions.
result SurvFD and SurvSHAP-IQ offer a new perspective on survival explanations, explicitly characterizing feature interactions.
Proposes a deep learning model for probabilistic forecasting that is also interpretable.
problem Inability to explain predictions of neural network-based time series forecasting methods.
method Deep Autoregressive Networks (DANLIP) for locally interpretable probabilistic forecasting.
result DANLIP provides interpretable predictions with comparable performance to state-of-the-art methods.
Interpretable deep learning model for insurance pricing.
problem Developing transparent yet accurate insurance pricing models.
method Developed a novel deep learning model with interpretable components.
result The model outperforms traditional methods in prediction accuracy.
New method visualizes tabular feature semantics for better model understanding.
problem Lack of feature interaction interpretation in tabular ML models.
method Feature Vectors method for global tabular dataset interpretability.
result Visualizes semantic relationships among tabular features.
Enhances tensor regression for interpretability and performance.
problem Interpreting and modeling multidimensional tensor data with structural heterogeneity.
method Generalized Nonnegative Structured Kruskal Tensor Regression (NS-KTR) with hybrid regularization and nonnegativity constraints.
result NS-KTR outperforms conventional methods in synthetic and real hyperspectral datasets.
An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully engineered patterns to distinguish adversarial inputs from their genuine counterparts…
Improved DSSMs for easier interpretable latent variables.
problem Complex and hard-to-interpret latent variables in DSSMs.
method Simplified predictive decoder and shrinkage priors.
result Interpretable latent variables improve forecasting performance.
BDH model learns like the brain, rivaling Transformer performance.
problem Leveraging brain-like properties for machine learning.
method Scale-free biologically inspired network of neuron particles.
result BDH model achieves Transformer-like performance with interpretability.
Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data. Far less attention has been paid to making these generative models interpretable. In many scenarios, ranging from scientific applications to finance, the observed variables have a natural groupi…
A new framework for private Bayesian tests maintains interpretability and computational efficiency.
problem Lack of interpretability and inability to quantify evidence in confidential data.
method Differentially private Bayesian tests based on test statistics.
result Established results on Bayes factor consistency under the proposed framework.
A new framework for interpretable models using sparse linear layers.
problem Performance degradation and lower interpretability in concept bottleneck models.
method Contrastive Language Image models and a single sparse linear layer with Bayesian inference.
result Our framework outperforms recent CBM approaches in accuracy and concept sparsity.
LDA-XGB1 balances fairness and accuracy in lending models.
problem Fair lending practices and model interpretability in binary classification.
method Biobjective optimization using binning and information value, leveraging XGBoost.
result Achieves effective balance between accuracy, fairness, and interpretability.
The workshop focuses on AI principles for structured data.
problem Using AI on structured data for decision-making.
method Addressing principles of privacy, accountability, interpretability, robustness, and reasoning.
result Designing approaches to use structured data for reliable decisions.
We develop a model of issue-specific voting behavior. This model can be used to explore lawmakers' personal voting patterns of voting by issue area, providing an exploratory window into how the language of the law is correlated with political support. We derive approximate posterior inference algorithms based on variat…
Paper introduces a hybrid GPR model for more interpretable RUL prediction in aeroengine.
problem Challenges in interpreting and modeling uncertainty in RUL prediction models.
method Modified Gaussian Process Regression (GPR) with temporal feature extraction.
result Effective prediction of RUL intervals with transparent feature significance.
Combining additive models and neural networks allows to broaden the scope of statistical regression and extend deep learning-based approaches by interpretable structured additive predictors at the same time. Existing attempts uniting the two modeling approaches are, however, limited to very specific combinations and, m…
The paper tackles inconsistency in removal-based explanations and proposes methods to reduce it.
problem Inconsistency in removal-based explanations.
method Established the Impossible Trinity Theorem and proposed two novel algorithms to minimize interpretation error.
result The proposed methods achieve a substantial reduction in interpretation error, up to 31.8 times lower.
Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners. Their reported empirical success however lacks solid theoretical interpretations for its inherent mechanism. In this paper, we reformulate thei…
Paper proposes PI-DAE for missing data imputation in buildings using physics constraints.
problem Missing data in building energy modeling.
method Physics-informed Denoising Autoencoders (PI-DAE) with multivariate and univariate configurations.
result Enhanced interpretability and robustness to missing data rates.
GAM(L)A model improves interpretability of machine learning models.
problem Interpretable machine learning models for high predictive performance.
method Combines partial linear models with variable selection for accurate prediction and interpretability.
result GAM(L)A outperforms parametric models and is comparable to black-box models like random forest and gradient boosting.
Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees, are inherently human-interpretable, which has not been empirically tested. Addi…
New methods for assessing and visualizing feature groups in machine learning models.
problem Lack of methods for interpreting feature groups in machine learning models.
method Permutation-based, refitting, and Shapley-based techniques for grouped feature importance. Introduced a sequential procedure for identifying stable feature combinations. Developed a combined features effect plot.
result Effective methods for assessing and visualizing the importance and effect of feature groups in machine learning models.
Interpretable AI model boosts investment confidence and profitability.
problem Challenges in financial forecasting and interpretability in decision-making models.
method SHAP-based explainability technique for interpretable AI models.
result Notable enhancement in investor's portfolio value.
We describe the underlying probabilistic interpretation of alpha and beta divergences. We first show that beta divergences are inherently tied to Tweedie distributions, a particular type of exponential family, known as exponential dispersion models. Starting from the variance function of a Tweedie model, we outline how…
NCL improves interpretability of deep features by enforcing non-negativity.
problem Lack of interpretability in deep representations.
method Non-negative Contrastive Learning (NCL) using non-negativity constraints.
result NCL outperforms standard contrastive learning in feature disentanglement and selection.
Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning. Nevertheless, deep learning models areopaque and often seen as black boxes. Thus, the…
Proposes a new method for interpreting feature importance and effects in dependent feature models.
problem Challenges in interpreting feature importance when features are dependent and interactions are present.
method Conditional Subgroup Approach
result Conditional PFI and PDP estimates based on this approach often outperform existing methods.
A new framework evaluates large language models efficiently and accurately.
problem Evaluation of large language models is challenging due to stochasticity and heterogeneity of benchmarks.
method Interpretable and scalable framework based on Item Response Theory (IRT) and majorization-minimization principle.
result Our method achieves superior scalability and interpretability compared to existing approaches.
New method adds all interactions in non-linear models without high computational cost.
problem Missing interactions in interpretable machine learning models.
method Additive higher-order factorization machines using tensor product splines.
result Scalable model with interactions at low computational cost.