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.
Proposes a method for explaining black-box models with nested feature attributions.
problem Making black-box models transparent and trustworthy.
method Model-agnostic local explanation method exploiting nested feature structure and consistency property.
result Accurate and consistent HiFAs and LoFAs estimated using fewer model queries.
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.
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.
Gaussian OBFS proves strong consistency in feature selection with correlations.
problem Feature selection consistency in the presence of correlations.
method Proves strong consistency of Gaussian OBFS under mild conditions.
result Identifies selected features and rates of convergence for different feature types.
Improves transparency of deep neural networks through feature and consistency analysis.
problem Black-box nature of deep learning inference limits transparency for safety-critical systems.
method Structural and linguistic feature analysis, consistency analysis.
result 75% of human workers found input data and results consistent, 70% found inference and results consistent.
Paper analyzes consistency between neural networks at different levels.
problem Understanding knowledge consistency between neural networks.
method Generic definition and task-agnostic method to disentangle consistent knowledge.
result Knowledge consistency provides new insights and can improve network performance.
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.
Analyzes feature learning in neural networks using a self-consistent dynamical field theory.
problem Feature learning in infinite-width neural networks.
method Constructs deterministic dynamical order parameters as inner-product kernels for hidden unit activations and gradients.
result Reveals the hidden layer activation distribution, neural tangent kernel evolution, and output predictions.
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.
Sublinearly structured DNNs achieve feature learning consistency for compositional functions.
problem Achieving feature-learning and prediction consistency in deep neural networks.
method Sublinearly structured DNNs
result Sublinearly structured DNNs match or surpass wide DNNs in prediction.
We characterize the class of exchangeable feature allocations assigning probability Vn,k∏l=1kWmlUn−ml to a feature allocation of n individuals, displaying k features with counts (m1,…,mk) for these features. Each element of this class is parametrized by a countable matrix V…
Paper solves feature selection for two distributions without parametric assumptions.
problem Feature selection for two different probability distributions.
method Sparsest k-subgraph problem formulation for nonparametric feature selection.
result Consistent estimator of features under mild conditions.
Graph Laplacian spectrum serves as a robust feature representation.
problem Difficulties in analyzing and comparing graphs due to their structure.
method Proposes using the graph Laplacian spectrum (GLS) as a feature representation.
result Graph Laplacian spectrum (GLS) preserves structural information and is consistent under deformation and invariance under isomorphism.
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.
A novel validation method improves feature importance analysis in subject-specific ML models.
problem Limited effectiveness of general ML models trained on large datasets for individual patient outcomes.
method A novel validation approach using a general ML model with repeated trials and random seed variation.
result Consistent identification of key features at the subject level and improved group-level feature importance analysis.
Contrastive regularization improves semi-supervised learning by better propagating confident pseudo-labels.
problem Consistency regularization's limitation in high performance and efficiency.
method Proposes contrastive regularization to update model features, pushing confident labels into unlabeled samples.
result Improves semi-supervised learning tasks with fewer training iterations and robust performance.
New decentralized KRR algorithm adapts to node-specific data.
problem Consistent node-specific data in decentralized KRR.
method Data-dependent random features for adaptive RF generation.
result Average regression accuracy improved by 25.5% across six datasets.
Theory captures feature learning effects in finite CNNs.
problem Feature learning in finite deep neural networks.
method Derive a self-consistent Gaussian Process theory.
result Good agreement with experiments and sharp transition between regimes.
FSinR is a comprehensive R package for feature selection.
problem Feature selection in machine learning.
method Filter and wrapper methods, search algorithms.
result Provides a variety of feature selection methods and search algorithms.
OBF optimally filters features under independent Gaussian models.
problem Biomarker discovery from complex data.
method Optimal Bayesian feature selection under independent Gaussian models.
result OBF is consistent and optimal under mild conditions.
Random forests are a type of ensemble method which makes predictions by combining the results of several independent trees. However, the theory of random forests has long been outpaced by their application. In this paper, we propose a novel random forests algorithm based on cooperative game theory. Banzhaf power index …
Variable screening is a fast dimension reduction technique for assisting high dimensional feature selection. As a preselection method, it selects a moderate size subset of candidate variables for further refining via feature selection to produce the final model. The performance of variable screening depends on both com…
A new feature selection method using random forest and Kolmogorov filter.
problem Ultra-high dimensional data feature selection.
method Fused Kolmogorov filter with random forest based recursive feature elimination.
result Selection and L2 consistency under weak conditions. 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.
Stabilizes linear models for clinical adoption by detecting feature correlations.
problem Instability of sparse high-dimensional models hinders clinical adoption.
method Regularizes latent correlation in features using an autoencoder network.
result Significant improvement in feature stability and model estimation stability.
Paper investigates random feature approximation for KPCA, showing computational and statistical efficiency.
problem Scalability issues in kernel methods for big data.
method Random feature approximation for approximate KPCA.
result Approximate KPCA is both computationally and statistically efficient compared to KPCA.
Proposes a method to align and differentiate feature clusters for unsupervised domain adaptation.
problem Difficulty in obtaining labeled data for domain adaptation.
method Label propagation and cycle consistency to align feature clusters.
result Successfully formed aligned and discriminative clusters for better domain adaptation.
Consistency distillation reduces memorization in diffusion models without harming sample quality.
problem Understanding how distillation affects memorization in diffusion models.
method Analysis of consistency distillation in diffusion models using a random feature neural network model.
result Consistency distillation reduces memorization in diffusion models without harming sample quality.
Paper proposes a novel unsupervised feature learning approach for environmental sound classification.
problem Classifying environmental sounds without labeled data.
method Cycle-consistent GAN for high-level data augmentation, unsupervised feature learning, codebook construction.
result Improves classification rate by 3.51% to 14.34% compared to state-of-the-art classifiers.
Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces…
New method improves tree ensemble feature attribution.
problem Inconsistent feature attribution methods in tree ensembles.
method Game theory and SHAP (SHapley Additive exPlanation) values.
result Developed consistent and locally accurate SHAP values.
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.
New method improves feature importance attribution for tree ensembles.
problem Inconsistent feature attribution methods for tree ensembles.
method Developed fast exact solutions for SHAP values, which are consistent and locally accurate.
result Improves supervised clustering performance by using SHAP values.
Paper tackles non-credible reviews by deriving consistency features from limited data.
problem Identifying credible online reviews amidst fake, incompetent, and biased reviews.
method Uses latent topic models to derive consistency features from review texts, item ratings, and timestamps.
result Improves credibility detection over state-of-the-art baselines on real-world datasets.
Large learning rates cause oscillations in NN weights that improve generalization.
problem Improving generalization of neural networks trained with large learning rates.
method Theoretical analysis and feature-noise data generation model.
result Oscillating SGD with large learning rates benefits NN generalization by effectively learning weak features.
Model classifies environment sounds using multiple feature channels and attention mechanisms.
problem Environment sound classification task.
method Multiple feature channels (MFCC, GFCC, CQT, Chromagram) and attention mechanism in a deep CNN.
result Achieves state-of-the-art performance on three benchmark datasets.
A new framework for deep matrix factorizations improves model consistency and flexibility.
problem Inconsistent loss functions in deep matrix factorizations.
method Introduces two new loss functions and a generic optimization framework.
result Demonstrates improved model performance on synthetic and real data.
Paper extends RUMs with features to handle incomplete preferences and proves identifiability.
problem Learning preferences from incomplete and possibly noisy data.
method Generalized Mixture of Random Utility Models with features, proving identifiability and consistency of MLE.
result Proves consistency of Maximum Likelihood Estimation (MLE) for PL with features under certain conditions.
Random ReLU features are shown to be a universally consistent learning algorithm but struggle with complex functions.
problem Approximating complex functions with random ReLU features.
method Study of random ReLU features through their RKHS and composition of functions.
result Random ReLU features can efficiently approximate complex functions but not as well as multi-layer ReLU networks.
Study tightens bounds for interpolating noisy data using minimum l1-norm.
problem Predicting noisy data with minimum l1-norm interpolation.
method Provided matching upper and lower bounds for prediction error.
result Tight consistency up to negligible terms for d≫n. New methods for better uncertainty prediction in ML.
problem Insufficient calibration in machine learning regression.
method Conditional calibration with respect to input features (adaptivity).
result Consistency and adaptivity are complementary, and good consistency does not guarantee good adaptivity.
Counterexamples show HSIC feature selection misses critical features.
problem Feature selection using HSIC misses important features.
method Feature selection via HSIC maximization.
result HSIC feature selection can miss critical features.
We develop an approach for feature elimination in statistical learning with kernel machines, based on recursive elimination of features.We present theoretical properties of this method and show that it is uniformly consistent in finding the correct feature space under certain generalized assumptions.We present four cas…
A new method scales sparse machine learning to ultra-high dimensional problems.
problem Sparse and interpretable machine learning in ultra-high dimensional data.
method Two-phase approach: backbone set determination followed by reduced problem solving.
result The backbone set contains truly relevant features with high probability.
This paper selects features in deep neural networks with theoretical guarantees.
problem Feature selection in deep neural networks with unknown nonlinear functions.
method Reformulate neural networks as index models, estimate feature sets using Stein's formula, and apply screening-and-selection mechanism.
result Consistent feature selection with theoretical guarantees, even in high-dimensional settings.
LLMs can select predictive features without seeing training data.
problem Selecting the best features for prediction tasks.
method Zero-shot prompting LLMs with feature names and task descriptions.
result LLMs consistently identify predictive features across various mechanisms.
This paper presents Correlated Nystrom Views (XNV), a fast semi-supervised algorithm for regression and classification. The algorithm draws on two main ideas. First, it generates two views consisting of computationally inexpensive random features. Second, XNV applies multiview regression using Canonical Correlation Ana…