CrystalCandle creates user-friendly explanations for machine learning models.
problem Low trust in predictive models due to lack of interpretability.
method End-to-end pipeline for model interpretation, including Model Importer, Interpreter, Narrative Generator, and Exporter.
result CrystalCandle leads to higher adoption rates and improved downstream metrics.
This paper enhances LSTM neural networks for multi-variable time series data, providing interpretable insights.
problem Accurate prediction of multi-variable time series data with interpretable insights.
method Variable-wise hidden states and a mixture attention mechanism to model the generative process of the target variable.
result Enhanced prediction performance by capturing the dynamics of different variables.
Survey on causal interpretability models for machine learning.
problem Understanding and explaining the decisions made by machine learning models.
method Comprehensive survey on causal interpretable models.
result Evaluation metrics for interpretability are discussed.
ALICE combines feature selection and inter-rater agreeability for ML model insights.
problem Improving interpretability of black box machine learning models.
method Integrates feature selection and inter-rater agreeability into a user-friendly Python library.
result Initial experiments on customer churn modeling show promising insights.
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.
GAMLA learns manifold structures with auto-encoding for global insights.
problem Limited global insight and lack of interpretable analytical descriptions in manifold learning.
method Two-round auto-encoding process to derive character and complementary representations.
result GAMLA provides global and analytical descriptions of smooth manifolds.
Paper simplifies complex sports analytics models for better understanding.
problem Difficulty in interpreting deep learning models for sports analytics.
method Developed a linear model tree that mimics deep learning models and explains its knowledge.
result The linear model tree achieves high accuracy and provides actionable insights.
FRED explains text model predictions by identifying key words and providing counterfactual examples.
problem Lack of interpretable methods for text models that are complex, lack foundations, and have unguaranteed performance.
method FRED identifies minimal influential word sets, assigns token importance, and generates counterfactual examples.
result FRED provides reliable and effective explanations for text model predictions.
New method interprets deep embeddings for diabetes patient clustering.
problem Interpreting deep embeddings for disease progression.
method Patient clustering approach using deep embeddings.
result Clinically meaningful insights into diabetes progression patterns.
The study identifies patient subgroups with enhanced or diminished opioid treatment effects.
problem Lack of prescribing guidelines for opioids leading to adverse outcomes.
method Generative model using mixture distribution and sparsity to discover subgroups with treatment effects.
result Human-interpretable insights on subgroups with enhanced or diminished treatment effects.
TS-Insight visualizes Thompson Sampling for better debugging and trust.
problem Thompson Sampling's black box nature hinders debugging and trust.
method TS-Insight is a visual analytics tool that traces evolving posteriors and evidence counts.
result Visualizations help in verifying, diagnosing, and explaining Thompson Sampling dynamics.
ADHAM provides interpretable survival analysis for healthcare.
problem Limited interpretability in deep learning survival models.
method Additive Deep Hazard Analysis Mixtures (ADHAM) with latent subgroup structure.
result ADHAM offers interpretable insights into exposure-outcome associations.
BRACE generates efficient counterfactual explanations by integrating causal reasoning.
problem Challenges in traditional counterfactual explanations, especially neglecting causal relationships.
method Backtracking counterfactuals with causal reasoning.
result Our method provides deeper insights into model outputs and is computationally efficient.
TFT improves multi-horizon forecasting with interpretable insights.
problem Complex multi-horizon forecasting with mixed inputs.
method Attention-based Temporal Fusion Transformer combining recurrent and self-attention layers.
result Significant performance improvements over existing benchmarks.
AdaptHetero uses MLI to tailor EHR models for subgroup-specific predictions.
problem Lack of subgroup-specific, operationalizable modeling strategies in EHRs.
method Integrates MLI with unsupervised clustering to identify subgroup-specific characteristics.
result Improves predictive performance by up to 174.39 percent across many subpopulations.
We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding. Our key insight is that interpretability is not an absolute concept and so we define it relative to a target model, which may or may not be a human. We define a framework that allows for comparin…
Proposes an interpretable machine learning framework for multi-arm HTE estimation.
problem Challenges in estimating heterogeneous treatment effects in multi-arm settings.
method Rule-based ensemble approach for HTE estimation in multi-arm trials.
result Achieved lower bias and higher estimation accuracy compared to existing methods.
Paper explores balancing market dynamics and interpretable forecasting models for energy prices.
problem Tackles the challenge of accurately predicting mFRR price and understanding market dynamics.
method Compares XGBoost and EBM for forecasting mFRR activation price in the balancing market.
result EBM provides comparable forecasting accuracy to XGBoost but with higher interpretability.
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.
Interpretable ML helps discover insights from big data.
problem Validating data-driven discoveries from complex datasets.
method Statistical and machine learning techniques for interpretable models.
result Challenges in validating data-driven discoveries remain.
Boosted additive models reveal new insights and potential pathologies.
problem Theoretical understanding of boosted additive models (BAMs) and their convergence behavior.
method Study of solution paths of BAMs and derivation of convergence results.
result Uncovering pathologies of boosting for certain additive model classes.
Explaining neural network computation in terms of probabilistic/fuzzy logical operations has attracted much attention due to its simplicity and high interpretability. Different choices of logical operators such as AND, OR and XOR give rise to another dimension for network optimization, and in this paper, we study the o…
This paper provides a guide to feature importance methods for better scientific inference.
problem Limited understanding of data-generating process due to opaque ML model mechanisms.
method Comprehensive review and new proofs of global feature importance methods.
result Facilitates a thorough understanding and concrete recommendations for FI methods.
We consider the problem of matrix completion on an n×m matrix. We introduce the problem of Interpretable Matrix Completion that aims to provide meaningful insights for the low-rank matrix using side information. We show that the problem can be reformulated as a binary convex optimization problem. We design Opt…
With the rise of deep neural networks for quantum chemistry applications, there is a pressing need for architectures that, beyond delivering accurate predictions of chemical properties, are readily interpretable by researchers. Here, we describe interpretation techniques for atomistic neural networks on the example of …
TabNet learns tabular data with attention, improving performance and interpretability.
problem Efficient learning and interpretability in tabular data.
method Sequential attention to feature selection, self-supervised learning.
result Outperforms other models on tabular datasets, interpretable feature attributions.
State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of magnitudes, in terms of understanding the way the model functions, we are often facing a …
Bayesian model improves data-efficiency in reinforcement learning.
problem Data inefficiency in reinforcement learning.
method Bayesian approach with variational inference.
result Human-interpretable insight into reinforcement learning dynamics.
The current work characterizes the users of a VoD streaming space through user-personas based on a tenure timeline and temporal behavioral features in the absence of explicit user profiles. A combination of tenure timeline and temporal characteristics caters to business needs of understanding the evolution and phases o…
Model-agnostic interpretation methods can mislead if not used carefully.
problem Misinterpretation of machine learning models due to improper use of techniques.
method General pitfalls of model-agnostic interpretation methods.
result Many pitfalls exist when using global interpretation techniques for machine learning models.
Transformers interpret as probabilistic mixtures, offering new insights.
problem Understanding Transformers from a probabilistic perspective.
method Modeling Transformers as mixtures of Gaussian models.
result Transformers can be seen as maximum posterior probability estimators.
New strategy uses interpretability to improve adversarial learning.
problem Improving adversarial learning speed and effectiveness.
method Spatially constrained one-pixel adversarial perturbations guided by gradient-based interpretability.
result Spatially constrained one-pixel adversarial perturbations noticeably improve convergence and attack success.
The chapter improves deep learning models by interpreting and improving their performance.
problem Deep learning models often lack interpretability, leading to poor understanding of their predictions.
method The approach involves attributing importance to features and feature groups, including interactions, to improve model performance.
result The proposed attributions provide insights across various domains and can be used to improve model generalization.
The paper investigates interpretability techniques for deep learning models in medical data.
problem Understanding the logic behind predictions of black-box models in medical decision-making.
method Applied deep neural networks and random forests to a medical dataset. Used autoencoders and local interpretable models to provide insights.
result Local interpretable models and autoencoders provide meaningful insights into cancer predictions, identifying distinct and non-generalizable features.
Study evaluates deep learning models for solar flare prediction with interpretability analysis.
problem Lack of interpretability in deep learning models for solar flare prediction.
method Proximity-based metric for analyzing attribution maps generated by Guided Grad-CAM.
result Models' predictions align with active region characteristics, offering insights into their behavior.
Study detects and explains positional bias in financial LLMs.
problem Positional bias in financial decision-making using LLMs.
method Unified framework and benchmark for detecting and quantifying bias in Qwen2.5 models.
result Positional bias is pervasive, scale-sensitive, and resurfaces under nuanced prompt designs.
SPLICE method disentangles shared and private latent variables from multi-view data.
problem Lack of methods to characterize nonlinear relationships and preserve geometric information in multi-view data.
method Neural network-based approach to infer disentangled, interpretable representations of shared and private latent variables.
result SPLICE yields more interpretable representations by preserving geometry and is more robust to incorrect latent dimensionality.
Novel framework explains machine learning models using ontology-based sampling.
problem Generating precise and insightful explanations for machine learning models.
method Ontology-based sampling technique and learnable anchor algorithm.
result Our approach generates more precise and insightful explanations.
The paper explores how to handle uncertain evidence in probabilistic models.
problem Handling uncertain evidence in probabilistic models and stochastic simulators.
method The paper considers distributional evidence, Jeffrey's rule, and virtual evidence as methods for interpreting uncertain evidence.
result The paper provides guidelines on how to account for uncertain evidence and highlights the importance of careful consideration.
We use PDPs with confidence bands to explain HPO results.
problem Lack of explainable insights into HPO results.
method Use IML techniques, specifically PDPs, with estimated confidence bands.
result Increased quality of PDPs in relevant sub-regions.
Simplified SGD interpretation as Ito process for broader applicability.
problem Lack of generality in current SGD interpretation.
method Introduced a simplified scheme for discrete-time approximation of Ito process.
result Flexibly interprets SGD and SGLD, providing insights into their asymptotic properties.
Deep learning benchmarks ECG analysis with strong performance.
problem Lack of appropriate datasets and evaluation procedures for ECG interpretation.
method Benchmarking on PTB-XL and ICBEB2018 datasets using convolutional neural networks.
result Convolutional neural networks, especially resnet- and inception-based architectures, outperform feature-based algorithms.
Interprets feature interactions in ad-click prediction models.
problem Improving interpretability of black-box recommender systems.
method Interprets feature interactions from a source model and encodes them in a target model.
result Interpretations significantly outperform existing recommender models.
LIME explanations can be uncertain, even for accurate models.
problem Uncertainty in LIME explanations undermines trust in machine learning models.
method Demonstrated two sources of uncertainty in LIME: sampling randomness and varying interpretation quality.
result Uncertainty in LIME explanations is present even in high-performing models.
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.
Curvature penalties improve interpretability of KANs without sacrificing accuracy.
problem Pathologically high-curvature oscillations in KANs activations make them hard to interpret.
method Derived a curvature penalty and proved an upper bound on model curvature.
result KANs with curvature penalties achieve substantially smoother activations while maintaining accuracy.
In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked …
Improves interpretability of graph representation learning models.
problem Limited insight into graph representation learning models.
method Exploration of methods to interpret node embeddings and creation of an evaluation framework.
result Improved ability to recover graph structure in downstream tasks.