A scalable algorithm compresses large categorical feature vocabularies while maximizing mutual information.
problem Learning from categorical features with very large vocabularies.
method Submodular optimization to maximize mutual information between compressed feature and target labels.
result The algorithm achieves a 63% approximation of the global optimal solution for mutual information.
Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic spe…
Chromatic Learning reduces feature dimensions for sparse datasets.
problem Sparse, high-dimensional data challenges traditional learning methods.
method Graph coloring over co-occurrence graph to create dense feature representation.
result Compresses sparse datasets significantly while maintaining model accuracy.
In human cognition, the expansion of perceived between-category distances and compression of within-category distances is known as categorical perception (CP). There are several hypotheses about the causes of CP (e.g., language, learning, evolution) but no functional model. Whether CP is essential to categorisation or …
Novel simplex-valued distribution improves on existing models.
problem Limitations of existing simplex-valued distributions like Dirichlet.
method Introducing continuous categorical distribution.
result Continuous categorical resolves limitations of Dirichlet.
New taxonomy and evaluation of neural network compression methods.
problem Efficiency of deep neural networks in real-world applications.
method Categorization and evaluation of tensor factorization and probabilistic compression methods.
result SVD and probabilistic compression methods are complementary and give the best results.
Proposes a new method for clustering compressed data.
problem Limited communication bandwidth and low-power consumption.
method Joint Variational Autoencoders with Bernoulli mixture models (VAB).
result The model can perform clustering in the compressed data domain.
This study compresses BERT to make it suitable for low-capability devices.
problem Large Transformer models are resource-intensive.
method Survey and analysis of model compression techniques for BERT.
result Insights into best practices for compressing large-scale Transformer models.
Efficiently fits stratified models with Laplacian regularization for categorical features.
problem Traditional stratified models fit separate models for each categorical value, which can be inefficient and lack flexibility.
method Proposes a distributed ADMM method for fitting stratified models with Laplacian regularization.
result Improves model performance and allows fitting for categorical values not in training data.
The paper proposes a method to analyze categorical feature interactions in large datasets using graph covariance and LLMs.
problem Analyzing complex datasets with numerous categorical features and timestamps.
method Binarization of categorical features using one-hot encoding, computation of graph covariance, identifying significant feature pairs, and using LLMs to generate explanations.
result The method identifies meaningful feature pairs and potential data stories underlying categorical feature interactions.
Bayesian encoding improves lead scoring for WeWork using conjugate models.
problem Encoding high-cardinality categorical features for machine learning.
method Conjugate Bayesian models for categorical features, ensemble learning.
result AUC improved from 0.87 to 0.97 for WeWork's lead scoring engine.
A novel graph spectral method for mixed categorical and numerical data.
problem Feature learning for mixed data types (numerical and categorical).
method Graph spectral decomposition of the graph Laplacian to model probabilistic dependence structure.
result Increased separability and clusterability of observations in the transformed feature space.
The paper shows how integrating categorical semantics can enhance unsupervised domain translation.
problem Improving unsupervised domain translation between perceptually different domains.
method Learning invariant categorical semantic features in an unsupervised manner and conditioning them on the style encoder.
result Conditioning the style encoder on learned categorical semantics improves translation and stylization.
Probabilistic hash embeddings improve online learning of categorical features.
problem Online learning of categorical features with changing vocabulary.
method Probabilistic hash embedding (PHE) with Bayesian online learning.
result PHE mitigates forgetting and maintains high performance in online settings.
In this paper, we present a new wrapper feature selection approach based on Jensen-Shannon (JS) divergence, termed feature selection with maximum JS-divergence (FSMJ), for text categorization. Unlike most existing feature selection approaches, the proposed FSMJ approach is based on real-valued features which provide mo…
Novel GLMMNet model tackles high-cardinality categorical features in actuarial applications.
problem Inadequate encoding methods for high-cardinality categorical features in actuarial data.
method Generalised Linear Mixed Model Neural Network (GLMMNet) integrating a generalised linear mixed model in a deep learning framework.
result GLMMNet often outperforms or performs comparably with entity embedded neural networks, providing transparency.
Distributed sensors compress and send features to a fusion center for linear regression.
problem Efficiently compress and transmit features from distributed sensors to a fusion center under varying communication constraints.
method Designs a distributed and adaptive feature compression scheme using optimal quantizers and simple adaptive strategies.
result Demonstrates improved inference performance through simulated experiments.
CatGCN improves GCNs by modeling feature interactions for categorical node features.
problem Suboptimal initial node representations in GCNs due to lack of feature interaction modeling.
method Integrates explicit interaction modeling (local and global) into initial node representation learning for categorical node features.
result CatGCN enhances initial node representations through feature interaction modeling, leading to improved model performance.
Principal components analysis (PCA) is a well-known technique for approximating a tabular data set by a low rank matrix. Here, we extend the idea of PCA to handle arbitrary data sets consisting of numerical, Boolean, categorical, ordinal, and other data types. This framework encompasses many well known techniques in da…
Unsupervised clustering can reproduce categorization systems if features and metrics are correctly selected.
problem Reproducing expert-provided categorization systems using unsupervised clustering.
method Investigated using toy datasets and real-world fund categorization. Used appropriate feature selection and a supervised Random Forest-based distance metric.
result Unsupervised clustering can reproduce ground truth classes if features and metrics are correctly selected.
We propose a method to train generative adversarial networks on mutivariate feature vectors representing multiple categorical values. In contrast to the continuous domain, where GAN-based methods have delivered considerable results, GANs struggle to perform equally well on discrete data. We propose and compare several …
The study analyzes decision trees on real and categorical features, deriving bounds on their VC dimension and proposing improved pruning algorithms.
problem Understanding the generalization properties of decision trees on different types of features.
method Introducing partitioning functions, relating them to growth functions and VC dimension, and deriving bounds for decision stumps and trees of various structures.
result Exact VC dimension of decision stumps and improved pruning algorithms for binary trees.
CardiCat generates synthetic data for high-cardinality tabular datasets.
problem Learning complexities of high-cardinality categorical features in tabular data.
method Substitutes one-hot encoding with regularized dual encoder-decoder embedding layers.
result Generates high-quality synthetic data with a smaller parameter space.
BottleNet++ compresses deep learning features for efficient mobile inference.
problem Balancing computation and communication in mobile devices with deep learning models.
method End-to-end architecture with encoder, non-trainable channel layer, and decoder.
result Achieves high compression ratio and bandwidth reduction with minimal accuracy loss.
Natural Language Processing models help encode categorical process inputs.
problem Encoding categorical variables in industrial process modeling.
method Using NLP models for categorical variable encoding, combined with dimensionality reduction.
result Meaningful embeddings of categorical variables improve feature importance.
Paper tackles noisy labels by compressing feature representations.
problem Learning with noisy labels leads to overfitting and poor generalization.
method Introduces compression inductive bias using Dropout and Nested Dropout.
result Compression helps in combating label noise and improving performance.
Saec compresses recommendation system embeddings by clustering similar features.
problem Large embedding matrix in recommendation systems consumes excessive memory.
method Saec clusters similar features within a field to reduce embedding matrix size.
result Saec reduces embedding size by ~27x with no performance loss.
Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the Information Theory, which aims to rank the features with their discriminative capacity…
Decision forests learn to model text by evaluating categorical-set conditions.
problem Decision forests cannot directly model text features.
method Defined and learned conditions for categorical-set features, enabling efficient text modeling.
result Decision forests can now directly model text features.
Develops 2-categorical methods for multi-parameter persistence.
problem Fundamental limitations of traditional persistence modules.
method 2-categorical structures to capture hierarchical interactions.
result New invariants effectively characterize multidimensional topological features.
This paper compresses large datasets for efficient machine learning.
problem Efficiently processing large datasets for machine learning.
method Constructing a sketch of the dataset using random features and averaging, then learning from the sketch.
result The approach can perform machine learning tasks without full dataset access, preserving both information and privacy.
New methods encode high-cardinality string variables efficiently.
problem Efficient encoding of high-cardinality string categorical variables.
method Two approaches: Gamma-Poisson matrix factorization and min-hash encoder.
result Improves supervised learning with high-cardinality categorical variables.
Bayesian neural networks are compressed using feature and weight pruning based on posterior inclusion probabilities.
problem Efficiently compressing Bayesian neural networks to reduce computation cost and improve generalizability.
method Bayesian model selection principles are applied to obtain posterior inclusion probabilities for pruning and feature selection.
result Pruned models show better generalizability on simulated and real-world data.
Baseline injury categorization is important to traumatic brain injury (TBI) research and treatment. Current categorization is dominated by symptom-based scores that insufficiently capture injury heterogeneity. In this work, we apply unsupervised clustering to identify novel TBI phenotypes. Our approach uses a generaliz…
In this paper we present CatBoost, a new open-sourced gradient boosting library that successfully handles categorical features and outperforms existing publicly available implementations of gradient boosting in terms of quality on a set of popular publicly available datasets. The library has a GPU implementation of lea…
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
problem Low bitrate image compression maintaining quality and features.
method Hierarchical VQ-VAE with stochastic quantization and Markovian latent variables.
result High perceptual quality and semantic features at low bitrates.
Dirichlet pruning compresses neural networks by removing unimportant units.
problem Compressing large neural network models without sacrificing performance.
method Assigns Dirichlet distribution over network layers' units and uses variational inference to estimate parameters.
result Achieves state-of-the-art compression performance on larger architectures like VGG and ResNet.
Random Intersection Chains selects important interactions from categorical features.
problem Heavy computational burden in considering all interactions for categorical features.
method Randomly generates chains of intersections, estimates and selects frequent patterns.
result Selected patterns are the most frequent in the data set.
This research compares two encoding methods for categorical attributes in machine learning, affecting model fairness.
problem The impact of encoding protected categorical attributes on fairness in machine learning models.
method Comparison of one-hot encoding and target encoding methods.
result Target encoding can lead to more unfair models compared to one-hot encoding due to induced bias.
New approach for learning large Bayesian networks using feature clustering and compression.
problem Learning large Bayesian networks efficiently and accurately.
method Feature space clustering, compression, and Hill-Climbing algorithm with BIC and MI score functions.
result Potential for parallelizable block learning and improved structure accuracy.
Global compression method prunes deep neural networks efficiently.
problem Efficiently compress deep neural networks for resource-constrained devices.
method Global Sparse Momentum SGD for on-the-fly pruning.
result Automatically finds appropriate per-layer sparsity ratios without re-training.
One-bit quantization improves inference speed for Random Features models.
problem Efficient inference on resource-constrained devices.
method Analysis of one-bit quantization in Random Features model.
result Asymptotically, quantizing weights except the last incurs no loss in generalization error.
New compression technique reduces RNN size by 2-4x without sacrificing accuracy.
problem Large and compute-intensive RNNs on edge devices with run-time constraints.
method Hybrid Matrix Decomposition (HMD) splits weight matrix into unconstrained and rank-1 blocks.
result HMD achieves 2-4x compression with faster run-time and similar accuracy.
ctsfeatures R package analyzes categorical time series data.
problem Lack of tools for analyzing categorical time series data.
method Provides functions for extracting statistical features and constructing graphs.
result Package enables traditional machine learning tasks on categorical time series.
Improves robustness of information bottleneck framework with sparsity-inducing prior.
problem Fixed-dimensional priors restrict flexibility and restrict robustness.
method Sparsity-inducing spike-slab categorical prior that learns dimension distribution per data point.
result Improves accuracy and robustness compared to traditional priors and other methods.
Neural networks compress uninformative input directions, improving test error.
problem Data lie in a high-dimensional space but labels vary along a lower-dimensional manifold.
method One-hidden layer network trained with gradient descent, analyzing weight evolution and compression.
result Compression factor λ ∼ √p improves test error, with β Feature > β Lazy.
Improved isolation forest for better outlier detection.
problem Outlier detection in multivariate data.
method Random cuts across feature space, size of feature space, and point assignment information.
result Improved results in many situations without modifying tree structure.
DPERC efficiently estimates covariance matrices for mixed data with missing values.
problem Estimating covariance matrices for datasets with missing values and mixed features.
method Direct Parameter Estimation for Randomly Missing Data with Categorical Features (DPERC).
result DPERC outperforms other methods in estimating covariance matrices for mixed data with missing values.