Paper proposes OpenAPI to interpret PLM models without access to parameters.
problem Interpreting hidden predictive models without access to parameters.
method Closed-form solution using overdetermined linear equation systems.
result Exact and consistent interpretations for PLM models.
SAEs struggle with feature consistency across runs, hindering MI reliability.
problem Inconsistency of learned SAE features across different training runs.
method Propose using the Pairwise Dictionary Mean Correlation Coefficient (PW-MCC) to measure feature consistency.
result High levels of feature consistency (0.80 for TopK SAEs on LLM activations) are achievable with appropriate architectural choices.
A new method for interpretable regression using data-dependent coverings.
problem Creating interpretable regression function estimators.
method Data-dependent coverings to generate a covering of the feature space instead of a partition.
result Ensures consistency without the need for shrinking cells, reducing the number of covering elements.
Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with good interpretability (Doshi-Velez 2017). An important factor that leads to the lac…
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.
New algorithm consistently orients eigenvectors for machine learning.
problem Inconsistent eigenvector orientation in machine learning.
method Postprocesses well-established eigen calls to create consistently oriented eigenvectors.
result Interpretable time series of training weights in machine learning models.
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.
Proposes a method to learn sparse deep neural networks with theoretical guarantees.
problem Over-parameterized deep neural networks cause training, prediction, and interpretation difficulties.
method Frequentist-like method for sparse DNNs under Bayesian framework.
result Consistent sparse DNNs with at most O(n/log(n)) connections. Regularization improves stability and consistency of sparse autoencoders.
problem Varying features across random seeds and training choices in SAEs.
method Added L1 or L2 penalties on encoder and decoder weights.
result L2 regularization increases cross-seed feature consistency.
Study finds machine learning interpretations are often unstable and unreliable.
problem Reliability of machine learning interpretations in high-stakes domains.
method Stability study on global interpretations using tabular data.
result Popular interpretation methods are frequently unstable, less stable than predictions, and not associated with prediction accuracy.
Develops transparent global models consistent with local explanations.
problem Creating globally interpretable models that align with local explanations from black-box models.
method Custom boolean features from sparse local contrastive explanations are used to train a globally transparent model.
result Custom transparent models have higher local consistency compared to other strategies.
In this paper, we consider the exact triangles consisting of stable vector bundles on one-dimensional complex tori, and give a geometric interpretation of them in terms of the corresponding Fukaya category via the homological mirror symmetry.
Genetic Programming constructs features for physics experiments, improving classification accuracy.
problem Lack of interpretable feature construction for experimental physics.
method Combining Genetic Programming with dimensional consistency constraints.
result Constructed features improve classification accuracy by a significant margin.
SHAFF estimates Shapley effects efficiently even with dependent variables.
problem Challenges in estimating Shapley effects, especially with dependent variables.
method SHAFF uses random forests to estimate Shapley effects efficiently.
result SHAFF provides a fast and accurate estimate of Shapley effects.
Let (Xn,Xˇn) be a mirror pair of an n-dimensional complex torus Xn and its mirror partner Xˇn. Then, a simple projectively flat bundle E(L,L)→Xn is constructed from each affine Lagrangian submanifold L in Xˇn with a unitary local system $\mathcal{L} \righta…
We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than present a black box model and explain it afterwards, we provide a globally interpretable model that is as accurate as other neural networks. O…
WISCA generates consensus explanations from conflicting model-agnostic interpretability methods.
problem Conflicting explanations from diverse interpretability algorithms.
method WISCA integrates class probability and normalized attributions to generate consistent explanations.
result WISCA consistently aligns with the most reliable individual method, improving explanation reliability.
The paper defines a mathematical framework for measuring model interpretability.
problem Improving trust and understanding in machine learning models for complex decisions.
method Constructing interpretable steps in a sequence for various models, generalizing to a family of consistent measures.
result A formal definition of interpretability allows quantifying the tradeoff with predictive accuracy.
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
New method proves neural networks can select features consistently.
problem Feature selection for deep neural networks is challenging.
method Adaptive Group Lasso selection procedure with Group Lasso as the base estimator.
result Adaptive Group Lasso is selection-consistent for a wide class of neural networks.
Develops a forward variable selection method for interpretable random forest models.
problem Interpreting high-dimensional non-parametric models like random forests.
method Forward variable selection using CRPS as loss function, with hypothesis testing at each step.
result Method selects a smaller set of variables that optimizes predictive performance.
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.
TRUST improves tree models' accuracy while maintaining interpretability.
problem Piecewise-constant regression trees lack in predictive accuracy compared to black-box models.
method Combines Random Forest accuracy with interpretability of shallow trees and sparsity of linear models, using LLMs for explanations.
result TRUST outperforms other interpretable models in predictive accuracy and matches Random Forest's accuracy.
Study improves exchange rate forecasting using machine learning and interpretable methods.
problem Complexity and ambiguity in financial and economic systems make precise exchange rate predictions difficult.
method Developed a fundamental-based model using machine learning and interpretability methods.
result Crude oil is the leading factor determining exchange rate dynamics, with significant events affecting its contribution.
The paper introduces a method for interpretable principal component analysis of high-dimensional time series.
problem Inconsistent and difficult-to-interpret principal component estimates in high-dimensional regimes.
method Localized sparse principal component analysis of spectral density matrices in frequency domain.
result Efficient algorithm for sparse-localized estimates of principal subspaces.
We propose a method for building an interpretable recommender system for personalizing online content and promotions. Historical data available for the system consists of customer features, provided content (promotions), and user responses. Unlike in a standard multi-class classification setting, misclassification cost…
Reducing ICD-10 code granularity improves cost model accuracy and stability.
problem High-dimensional regression with ICD-10 codes leads to unstable coefficient estimates.
method Log-linear analytics approach to cost model regularization through diagnostic code merging.
result Reducing ICD-10 code granularity from 7 characters to 6 or fewer improves model interpretability and consistency.
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.
The paper studies how neural policies can be interpreted using decision trees.
problem Understanding how machine learning controllers make decisions in complex environments.
method The approach involves disentangled representation using decision trees to interpret neural policies.
result The paper shows that disentanglement of learned neural dynamics improves interpretability.
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the reason why it performs quite well becomes a challenging question. In this paper,…
In the context of post-hoc interpretability, this paper addresses the task of explaining the prediction of a classifier, considering the case where no information is available, neither on the classifier itself, nor on the processed data (neither the training nor the test data). It proposes an instance-based approach wh…
Study embeds PC matrices into Grassmannian manifold for geometric interpretation.
problem Understanding algebraic consistency of pairwise comparisons matrices.
method Leverages Plücker coordinates and geometric interpretation of Grassmannian manifold.
result Algebraic consistency condition is equivalent to geometric consistency in G(2,n). Adaptive Group Lasso selects important features in neural networks.
problem Lack of interpretability in neural networks.
method Adaptive Group Lasso for feature selection.
result Consistent feature selection for neural networks with theoretical guarantee.
A new tree-based estimator, FastPD, efficiently estimates PD functions for machine learning models.
problem Efficiently estimating Partial Dependence functions for machine learning models.
method Proposes a new tree-based estimator, FastPD, to estimate PD functions.
result FastPD consistently estimates the desired population quantity and improves complexity from quadratic to linear.
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 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…
We give a topological interpretation of the space of L2-harmonic forms on finite-volume manifolds with sufficiently pinched negative curvature. We give examples showing that this interpretation fails if the curvature is not sufficiently pinched and that our result is sharp with respect to the pinching constants. The me…
New method enforces encoder sparsity in HPF for more interpretable feature selection.
problem Lack of encoder sparsity in HPF leads to lack of column-clustering property.
method Enforces encoder sparsity using a generalized additive model (GAM).
result Gains ability to perform feature selection and relates each representation to original features.
Knots and links are interpreted as homotopy classes of nanowords and nanophrases in an alphabet consisting of 4 letters. Similar results hold for curves on surfaces. We also discuss versions of the Jones link polynomial and the link quandles for nanophrases.
Proposes a decision-theoretic approach for enhancing model interpretability in Bayesian frameworks.
problem Challenges the traditional approach of restricting model structure for interpretability in Bayesian frameworks.
method Introduces an interpretability utility function and a two-step method involving a reference model and a proxy model.
result Demonstrates that the proposed method generates more accurate models with the same level of interpretability.
In this paper we introduce a flexible HJM-type framework that allows for consistent modelling of intraday, spot, futures, and option prices. This framework is based on stochastic processes with economic interpretations and consistent with the initial term structure given in the form of a price forward curve. Furthermor…
BICauseTree improves causal effect estimation by identifying clusters and balancing treatment allocation.
problem Improving interpretability and transparency in causal effect models from observational data.
method Hierarchical bias-driven stratification using decision trees with a customized objective function.
result BICauseTree provides interpretable causal effect estimation and is comparable to existing methods.
End-to-end learnable network for safer self-driving with interpretable intermediate representations.
problem Safe motion planning for self-driving vehicles.
method Differentiable semantic occupancy representation for cost calculation in motion planning.
result Significantly outperforms state-of-the-art planners in imitating human behaviors and producing safer trajectories.
Proposes a score to compare rule-based algorithms' interpretability.
problem Lack of consensus on interpretability for predictive models.
method Defines a score with three terms: predictivity, stability, and simplicity, each quantified by simple formulas.
result Compares interpretability of rule-based and tree-based algorithms for regression and classification.
A new Shapley value approach for neural networks interpretable and stable.
problem Neural networks' interpretability and training stability issues.
method Shapley value approximation for ReLU activation, globally continuous Shapley gradient, Shapley Activation function.
result SA consistently outperforms ReLU in training convergence, accuracy, and stability.
Study evaluates consistency of feature attribution in deep learning for multi-omics data.
problem Challenges in interpretability of deep learning models in biological research.
method Investigation of Shapley Additive Explanations (SHAP) on multi-view deep learning models applied to multi-omics data.
result SHAP rankings are sensitive to architecture and random initialization, suggesting caution.
The problem of change-point estimation is considered under a general framework where the data are generated by unknown stationary ergodic process distributions. In this context, the consistent estimation of the number of change-points is provably impossible. However, it is shown that a consistent clustering method may …
Energy-based diffusion models improve molecular sampling and simulation.
problem Inconsistency between diffusion model scores and equilibrium distributions.
method Fokker-Planck regularization to enforce consistency.
result Improved consistency and efficient sampling of biomolecular systems.