Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

137274411548 · Jun 202019922001200920182026
48 results for interpretation challenges

Researchers review challenges in interpreting additive models, especially neural additive models.

problem Challenges in interpreting additive models, particularly neural additive models.
method Review of generalized additive models and discussion of nonidentifiability.
result Challenges in claiming interpretability or suitability for safety-critical applications of additive models.

Brief history and challenges of interpretable machine learning.

problem Challenges in interpreting machine learning models, especially in scientific applications.
method Overview of state-of-the-art methods and discussion of challenges.
result Interpretable machine learning has a rich history but faces significant challenges.

Survey on principles and challenges of interpretable machine learning.

problem Improving machine learning models' interpretability for high-stakes decisions.
method Identification and analysis of 10 technical challenges in interpretable machine learning.
result Identification of 10 technical challenges in interpretable machine learning.

Interpreting machine learning models helps understand adversarial attacks and defenses.

problem Understanding model vulnerability to adversarial attacks.
method Model interpretation techniques to explore adversarial attacks and defenses.
result Interpretation methods can be applied to adversarial attacks and defenses.

Paper develops a credit scoring system for micro-loans, addressing interpretability and data quality challenges.

problem Developing a credit scoring system for micro-loans with interpretability and data quality concerns.
method Introduces semi-supervised algorithm to aid model development and evaluates its performance.
result Semi-supervised algorithm aids in model development and demonstrates improved performance.

The paper discusses challenges and proposed solutions for evaluating model explanations.

problem Challenges in evaluating model explanations for interpretability.
method Proposes a distinction between descriptive and persuasive explanations and discusses potential research directions.
result Evaluating model explanations using functional metrics may perpetuate cognitive bias.

This paper improves NLP interpretability by using sentence segments instead of words.

problem Limitations of word-based sampling in explaining complex BERT models.
method Using sentence segments as elementary building blocks for NLP interpretability.
result Improved fidelity of the explainer on a benchmark classification task.

BetaExplainer improves GNN interpretability by masking unimportant edges.

problem Interpreting GNNs' predictions is difficult due to black-box behavior and lack of uncertainty quantification.
method BetaExplainer uses a sparsity-inducing prior to mask unimportant edges during training.
result BetaExplainer provides uncertainty in edge importance and improves predictive accuracy on challenging datasets.

TopInG improves graph interpretability using persistent homology.

problem Lack of interpretability in Graph Neural Networks (GNNs).
method TopInG uses persistent homology to identify persistent rationale subgraphs in graphs.
result TopInG improves predictive accuracy and interpretability compared to state-of-the-art methods.

OpenViewer tackles multi-view learning challenges with interpretability and generalization.

problem Lack of interpretability and insufficient generalization in multi-view learning models.
method OpenViewer introduces a Pseudo-Unknown Sample Generation Mechanism, Expression-Enhanced Deep Unfolding Network, and Perception-Augmented Open-Set Training Regime.
result OpenViewer effectively addresses openness challenges and enhances recognition performance for both known and unknown samples.

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user interfaces. Thus, interpretability has become a vital concern in machine learnin…

2016-06-16abs ↗pdf ↗

ProtoPNet uses deep learning to classify images by identifying prototypical parts.

problem Challenging image classification tasks where understanding reasoning is important.
method ProtoPNet architecture that reasons by finding prototypical parts and combining evidence.
result ProtoPNet achieves comparable accuracy to non-interpretable models and provides interpretability.

VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.

problem Lack of higher-level structure interpretation in FLMs' attention weights.
method Formal definition of conceptual interpretation, variational Bayesian framework (VALC).
result VALC finds optimal language concepts for FLM predictions, providing concept-level interpretations.

Ploutos predicts stock movements with financial LLM, improving interpretability.

problem Combining textual and numerical data for stock prediction and lack of interpretability.
method Proposes Ploutos framework combining PloutosGen and PloutosGPT for interpretable predictions.
result Framework outperforms state-of-the-art methods in prediction accuracy and interpretability.

Enhances FAVAR models with autoencoder for better economic forecasting and interpretability.

problem Limitations of linear FAVAR models in forecasting and structural analysis.
method Introduces Grouped Sparse autoencoder with time-varying parameters.
result The Grouped Sparse autoencoder produces more interpretable factors and superior forecasting performance.

TCAV uses CAVs to interpret deep learning models by testing for concept importance.

problem Interpreting deep learning models due to their complexity and opaque internal state.
method Testing with CAVs (TCAV) using directional derivatives to quantify concept importance.
result Shows how CAVs can be used to explore hypotheses and generate insights in image classification and medical applications.

Proposes M-CHMM for robust modeling of multivariate healthcare time series.

problem Challenges in analyzing multivariate healthcare time series data.
method Mixture of coupled hidden Markov models (M-CHMM) with two sampling algorithms.
result Improves data fit, handles missing and noisy measurements, and enhances prediction accuracy.

The study explores statistical methods to interpret radiological models and identify key features.

problem Interpreting complex radiological models for clinical use.
method Exploration of statistical techniques to assess relationships between radiomic features.
result Identification of key relationships and features for improved interpretability.

This paper interprets neural network ECG models by breaking them into understandable components.

problem Lack of model interpretability in deep learning for medical applications.
method Factorizes neural network models into interpretable black box components using hierarchical equations.
result Demonstrates interpretable component models for ECG waveforms, improving model understanding and predictability.

GRAM addresses healthcare data insufficiency and interpretation challenges using graph-based attention.

problem Data insufficiency and lack of interpretability in healthcare predictive modeling.
method GRAM integrates EHR with medical ontologies, using attention mechanisms to represent medical concepts.
result GRAM outperforms RNN in accuracy and interpretability, using less data.

Spofe bridges statistical rigor and interpretability in feature extraction from tabular data.

problem Ensuring statistical rigor and interpretability in feature extraction from complex tabular data.
method Spofe combines kernel principal components and sparse polynomial functions with a multi-objective knockoff selection procedure.
result Spofe consistently outperforms other methods in feature selection for regression and classification tasks.

This technique learns interpretable models by encoding the training distribution as a Dirichlet Process and using uncertainty scores as an oracle.

problem Creating small, interpretable models that are still accurate.
method Exploits a Dirichlet Process to encode the training distribution, uses Bayesian Optimization for parameters, and projects data to one dimension using an uncertainty oracle.
result Improves accuracy and size trade-off, applicable across different model families.

Gradient Weighted Superpixels improve CNN interpretability without sacrificing speed.

problem Efficiency vs. interpretability trade-off in CNNs, especially for large input volumes.
method Gradient-based pixel scoring techniques applied to superpixels.
result Superpixels approximate LIME in a fraction of the time, improving interpretability.

WLDA enhances LDA for missing data, improving classification accuracy and interpretability.

problem Missing data in real-world datasets hinders classification accuracy and interpretability of LDA.
method WLDA incorporates a weight matrix to handle missing data directly, preserving interpretability.
result WLDA significantly outperforms traditional methods in datasets with missing values.

Motivation : Molecular signatures for diagnosis or prognosis estimated from large-scale gene expression data often lack robustness and stability, rendering their biological interpretation challenging. Increasing the signature's interpretability and stability across perturbations of a given dataset and, if possible, acr…

2010-01-18abs ↗pdf ↗

A new method reparameterizes ridge regression for faster, more interpretable results.

problem Challenges in selecting hyperparameter α for ridge regression.
method Fractional Ridge Regression (FRR) reparameterizes RR in terms of the ratio γ.
result FRR solutions vary with different γ, avoiding wasted calculations and manual exploration.

LIMIS improves locally interpretable models by selecting and distilling key instances.

problem Low fidelity of locally interpretable models.
method LIMIS uses instance-wise subsampling guided by policy gradient and reward to improve fidelity.
result LIMIS near-matches black-box model accuracy while significantly improving fidelity.

New interface explains contextual bandits to non-experts.

problem Interpreting and managing contextual bandits for non-expert operators.
method Developed a metric 'value gain' for off-policy evaluation and designed an interface to explain bandit behavior.
result Empowered non-experts to manage complex machine learning systems through accessible presentation.

Machine-generated interpretations do not improve users' guessing accuracy in image classifiers.

problem Determining the usefulness of machine-generated explanations for deep neural networks.
method Human evaluation of crowd workers guessing incorrectly predicted labels with and without visual interpretations.
result Showing machine-generated visual interpretations decreased average guessing accuracy by about 10%.

ProSeNet provides interpretable deep sequence models with natural explanations.

problem Challenges in explaining deep neural network predictions for sequence modeling.
method Prototypes derived from case-based reasoning, with criteria for simplicity, diversity, and sparsity.
result Achieves accuracy on par with state-of-the-art models while providing interpretable explanations.

Avoid explaining black box models; use interpretable ones instead.

problem High-stakes decisions made by black box models cause societal harm.
method Design inherently interpretable models instead of trying to explain black box models.
result Inherently interpretable models are a better approach for high-stakes decisions.

Unified framework for interpreting complex regression models with many predictors.

problem Interpreting nonparametric regression models with many predictors.
method Derivative-based approach for existing tools like partial-dependence plots.
result New technique called accumulated total derivative effects plot for complex models.

G-FIGS uses instance weights to create interpretable models from diverse data.

problem Generalizing to diverse data distributions while maintaining interpretability.
method Estimates group membership probabilities, uses as instance weights in FIGS to grow decision trees.
result Achieves state-of-the-art prediction performance and maintains interpretability.

Develops methods for making deep learning models more interpretable by answering counterfactual questions.

problem Lack of interpretability in deep learning models, especially in high-stakes applications.
method Introduces causal interpretability, a framework for building models that are causally interpretable by design.
result Identifies a fundamental tradeoff between causal interpretability and predictive accuracy.