QUACKIE creates a new benchmark for NLP interpretability.
problem Evaluating NLP interpretability methods is challenging due to biased ground truths.
method Formulated a custom classification task from question-answering datasets, generating unbiased ground truths.
result Demonstrated the effectiveness of current interpretability methods on the new benchmark.
New algorithm improves interpretability in sequence classification.
problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.
Paper interprets ResNets via gate-network controls and deep-layer classifications.
problem Understanding the performance mechanism of ResNets.
method Constructs typical solutions using gate-network controls and deep-layer classifications.
result Proves the universal-approximation capability of ResNets.
Adversarial regularization helps learn interpretable shapelets for time series classification.
problem Difficult to interpret learned shapelets in time series classification.
method Use of adversarial regularization to constrain model to learn more interpretable shapelets.
result Adversarially regularized method learns interpretable shapelets.
New method improves neural network interpretability against adversarial attacks.
problem Adversarial attacks can hide from neural network interpretability methods.
method Develops an interpretability-aware defensive scheme promoting robust interpretation.
result Achieves both robust classification and robust interpretation.
CRITS improves time series classification with interpretable local explanations.
problem Lack of detailed explanations in time series classification models.
method CRITS uses convolutional kernels, max-pooling, and rectified linear units to extract feature weights.
result CRITS provides intrinsically interpretable local explanations without requiring gradients or random perturbations.
New method visualizes decision boundaries of classification models.
problem Difficulty in understanding how classification models interpret data.
method Hybrid supervised-unsupervised technique for visualizing decision boundaries.
result Provides interpretable maps for qualitative and quantitative analysis.
FrequentNet uses frequency domain basis vectors for image classification, making models more interpretable and efficient.
problem Image classification models are often complex and hard to interpret.
method FrequentNet selects filter vectors from frequency domain basis vectors instead of training them with back propagation.
result The method improves interpretability and efficiency of image classification models.
Framework evaluates post-hoc interpretability methods in time-series classification.
problem Lack of suitable post-hoc interpretability methods for time-series classification.
method Proposes a framework with quantitative metrics to assess interpretability methods.
result Addresses several drawbacks of existing methods, including dependence on human judgement and data distribution shift.
Interpretable neural model for few-shot time-series classification.
problem Few-shot time-series classification challenges.
method Dual Prototypical Shapelet Networks (DPSN) framework.
result DPSN framework outperforms state-of-the-art methods, especially with limited data.
Transfer learning improves sparse, interpretable probabilistic classification.
problem Sparse and interpretable models in transfer learning.
method Two transfer learning extensions integrated into sparse and interpretable probabilistic classification vector machine.
result Transfer learning extensions improve sparsity and performance.
New method interprets multivariate time series for better results.
problem Difficulty in applying traditional methods to multivariate time series.
method Alternative representation of multivariate time series through features.
result Competitive and interpretable results achieved.
Proposes FairCORELS for fair, interpretable rule lists.
problem Fairness in interpretable models for high-stakes decisions.
method Multi-objective variant of CORELS, supporting fairness measures.
result Outperforms state-of-the-art fair classification techniques.
r-STSF improves TSC accuracy and interpretability.
problem Lack of interpretability in state-of-the-art TSC methods.
method Randomized-Supervised Time Series Forest (r-STSF) using interval-based approach and ensemble of randomized trees.
result r-STSF achieves state-of-the-art accuracy and enables interpretability.
Classy learns interpretable probabilistic rule lists for multiclass classification.
problem Creating interpretable multiclass classifiers that are both accurate and understandable.
method Probabilistic rule lists and minimum description length (MDL) principle for model selection.
result Classy selects small probabilistic rule lists that outperform state-of-the-art classifiers in terms of predictive performance and 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.
New linear models improve time series classification efficiency and interpretability.
problem Complex and inefficient classifiers limit interpretability and applicability to variable-length time series.
method Symbolic representations, multi-resolution, multi-domain, linear models.
result mtSS-SEQL+LR achieves similar accuracy to state-of-the-art methods but with lower time and memory usage.
Proposes interpretable time series classification through extracted features.
problem Interpretable time series classification in complex problems.
method Extracts features from time series to improve interpretability of traditional classifiers.
result No statistically significant differences in accuracy compared to state-of-the-art models.
New rule-based method for classification with scalability, interpretability, and fairness.
problem Developing a scalable and fair classification method.
method Column generation for linear programming, decision tree-based heuristic, and rule-based optimization.
result The method returns interpretable rules with optimal weights and addresses fairness constraints.
Interpretable deep learning classifies two-prong jets using jet spectra.
problem Lack of interpretability in deep learning for jet classification.
method Truncated Taylor series jet spectrum for interpretability.
result Interpretable network performs similarly to CNN but is simpler.
Simplifies F-measure for better interpretability.
problem Lack of intuitive interpretation of F-measure.
method Introduces F* (F-star) transformation.
result F* provides an immediate practical interpretation.
UniShape improves time series classification by selecting relevant subsequences.
problem Classifying time series data requires capturing interpretable shapelets.
method UniShape uses a shape-aware adapter to aggregate multiscale subsequences into class tokens.
result UniShape achieves state-of-the-art classification performance.
Scoring systems are classification models that only require users to add, subtract and multiply a few meaningful numbers to make a prediction. These models are often used because they are practical and interpretable. In this paper, we introduce an off-the-shelf tool to create scoring systems that both accurate and inte…
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules. We consider rules in both conjunctive normal form (AND-of-ORs) and disjunctive normal form (OR-of-ANDs). A principled objective function is proposed to trade …
The paper proposes simple models for interpretable predictions while maintaining privacy.
problem Balancing interpretability and privacy in complex machine learning models.
method Locally linear maps per class to approximate complex models, ensuring differential privacy.
result High classification accuracy with differentially private explanations.
ExMatrix visualizes RF models, aiding in decision understanding.
problem Lack of interpretability in complex models like RF.
method ExMatrix, a novel visualization method for RF interpretability.
result ExMatrix handles large, complex RF models and promotes interpretability.
FiberNet integrates geometry into machine learning for clearer classification.
problem Lack of interpretability in traditional deep learning.
method Reformulates classification as geometric optimization on fiber bundles, introducing learnable Riemannian metrics and variational prototype optimization.
result Clear geometric interpretability and efficiency in classification.
MOTGNN integrates multi-omics data for disease classification with improved accuracy and interpretability.
problem Challenges in integrating multi-omics data due to high dimensionality, heterogeneity, and lack of reliable interaction networks.
method MOTGNN uses XGBoost for graph construction, modality-specific GNNs for representation learning, and a deep feedforward network for cross-omics integration.
result MOTGNN outperforms state-of-the-art baselines by 5-10% in accuracy, ROC-AUC, and F1-score across three real-world disease datasets.
We propose to apply deep transfer learning from computer vision to static malware classification. In the transfer learning scheme, we borrow knowledge from natural images or objects and apply to the target domain of static malware detection. As a result, training time of deep neural networks is accelerated while high c…
Deep neural network models have been proven to be very successful in image classification tasks, also for medical diagnosis, but their main concern is its lack of interpretability. They use to work as intuition machines with high statistical confidence but unable to give interpretable explanations about the reported re…
Model interprets image classification using hierarchical prototypes.
problem Lack of hierarchical interpretation in vision models.
method Uses hierarchically organized prototypes to classify objects at each level of a taxonomy.
result Model interprets image classification at each level of the taxonomy.
Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or a linear model, are widely recognized as human-interpretable. However, such mode…
SIRUS creates interpretable rules from random forests for manufacturing.
problem Lack of interpretability in complex models for critical decisions.
method SIRUS is a classification algorithm based on random forests that produces a simple list of rules.
result SIRUS achieves stability and accuracy comparable to random forests.
Deep learning improves cancer report classification accuracy.
problem Automatically assigning ICD-O3 codes to cancer reports.
method State-of-the-art deep learning techniques, including hierarchical and flat models, with attention mechanisms.
result Best model achieves 90.3% accuracy on topography site assignment and 84.8% on morphology type assignment.
C2G-Net improves image classification of similar objects like cells.
problem Classifying images with many similar objects efficiently and interpretably.
method Combines image compression and a CNN with reduced parameters.
result C2G-Net achieves similar accuracy to conventional CNNs but with reduced training time and improved interpretability.
New framework models uncertainty in classification debates.
problem Weak interpretability of existing uncertainty quantification methods.
method Courtroom analogy and Mixture of Dirichlet Experts (MoDEX) model.
result MoDEX achieves state-of-the-art uncertainty quantification performance.
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.
MAGIC-Flow generates and classifies medical images with interpretability.
problem Challenges in generative modeling for medical imaging.
method Conditional multiscale normalizing flow architecture.
result MAGIC-Flow creates realistic, diverse samples and improves classification.
engGNN combines external and generated graphs to improve disease classification and biomarker discovery.
problem Challenges in integrating omics data due to high dimensionality and small sample sizes.
method Dual-graph framework that integrates external biological networks with data-driven generated graphs.
result engGNN outperforms state-of-the-art methods in disease classification and biomarker discovery.
GMT improves interpretability of XGNNs by approximating SubMT.
problem Limited understanding of existing interpretable subgraph learning methods.
method Formulated subgraph multilinear extension (SubMT) and designed GMT architecture.
result GMT outperforms state-of-the-art in both interpretability and generalizability.
Combines neural networks and STL for multi-class time-series classification.
problem Lack of interpretability in neural networks for time-series data.
method Proposes a method that uses neural networks to classify time-series data using STL specifications, introducing margin for multi-class classification and STL-based attributes for interpretability.
result Evaluations show improved interpretability and performance compared to state-of-the-art baselines.
Proposes new methods for interpreting document classification models.
problem Interpretation fragility of attention-based neural networks.
method Corpus-level and concept-based explanation methods using attention weights.
result Extracts semantically meaningful keywords and concepts for model predictions.
Proposes a method for selecting important variables in high-dimensional data.
problem High-dimensional classification problems with many noise variables.
method Probability-based nonparametric multiple-class classification method with variable selection.
result The method can have prediction power similar to Bayes rule and retains interpretability.
Proposes a method to improve GNN predictions by finding the most predictive subgraph.
problem GNNs aggregate all nodes and edges, making predictions hard to interpret.
method Uses reinforcement learning to find a sparse subgraph that optimizes graph classification performance.
result Our method finds sparser subgraphs that improve interpretability while maintaining performance.
ProtoryNet interprets text sequences using prototype trajectories for better understanding.
problem Improving text classification interpretability and accuracy.
method ProtoryNet uses prototype trajectories to interpret text sequences, with prototype pruning for better interpretability.
result ProtoryNet outperforms baseline models and reduces performance gap compared to black-box models.
Simplifies random forests by breaking down trees into rules for better interpretability.
problem Balancing model complexity and accuracy in random forests.
method Breaking down random forest trees into individual classification rules and selecting a subset.
result A few selected rules can achieve acceptable accuracy similar to the original model, leading to simpler models.
Novel approach for creating interpretable classifiers using bilevel optimization of split-rules in NLDTs.
problem Creating highly accurate and easily interpretable classifiers for practical applications.
method Representing classifiers as assemblies of simple mathematical rules using NLDTs with evolutionary bilevel optimization.
result The approach ensures interpretability while achieving high accuracy on various classification problems.
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…