DPFE extracts approved features privately, preserving sensitive information.
problem Protecting sensitive information while allowing feature extraction.
method Selective exchange of information, log-rank privacy measure, and smartphone implementation.
result DPFE achieves high accuracy for primary tasks while preserving sensitive feature privacy.
TIPRDC anonymizes data features to protect privacy while retaining useful information.
problem Privacy concerns from crowdsourced data hinder deep learning applications.
method Hybrid training method combining adversarial and mutual information estimation.
result Feature extractor hides private information while preserving original data features.
PILLAR improves SP learning with less private data.
problem Efficiently learning with semi-private data under privacy constraints.
method Uses pre-trained public data features to reduce private data requirements.
result Significantly lower private labelled sample complexity achieved.
Dual adversarial co-learning improves multi-domain text classification.
problem Improving text classification across multiple domains.
method Dual adversarial co-learning with shared-private networks and dual adversarial regularizations.
result Achieves state-of-the-art performance on multi-domain sentiment classification datasets.
Prototype extraction framework for domain adaptation.
problem Statistical distance minimization issues in unsupervised domain adaptation.
method Memory and computation-efficient probabilistic framework for class prototype extraction and feature alignment.
result Competitive performance with state-of-the-art methods, no additional model parameters required.
New private learning algorithms improve utility in tasks with public features.
problem Private learning with public features in recommendation and ad prediction.
method Developed algorithms that protect only certain sufficient statistics, improving utility for linear regression and private recommendation benchmarks.
result Achieved state-of-the-art performance on private recommendation benchmarks.
Private learning needs more data or better features.
problem Improving differentially private machine learning performance.
method Demonstrates the need for either more private data or better features.
result Private learning requires either more data or better features.
This paper applies secure multi-party computation to K-means clustering to protect private data.
problem Privacy-preserving K-means clustering for distributed private data.
method Secure multi-party computation (MPC) techniques to protect private data during K-means clustering.
result Privacy-preserving K-means clustering is feasible and effective for both horizontal and vertical data distribution.
Improved DLG extracts accurate labels from gradients, overcoming DLG's convergence issues.
problem Private training data leakage from shared gradients in distributed learning systems.
method Proposes iDLG, a simple approach to synthesize accurate labels from gradients.
result iDLG reliably extracts ground-truth labels from gradients, unlike DLG.
New method for private learning with public features improves convergence rates.
problem Private estimation with public features under local differential privacy.
method Semi-feature LDP, HistOfTree estimator.
result HistOfTree reaches mini-max optimal convergence rate.
Private method measures nonlinear correlations between data hosted across two entities.
problem Measuring nonlinear correlations between sensitive data hosted across multiple parties while preserving privacy.
method Differentially private estimator of distance correlation.
result First private estimator of nonlinear correlations in a multi-party setup.
Improved image generation with private data using perceptual features.
problem Difficulty in training generative models with differential privacy.
method Use pre-trained perceptual features to learn private data distribution.
result Generative models can generate high-quality images with low privacy budget (ϵ≈2). Paper evaluates and improves private feature selection methods.
problem Feature selection in high-dimensional datasets with privacy constraints.
method Correlations-based order statistic privatized for feature selection.
result Our method significantly outperforms established baseline for private feature selection.
Hermite polynomials improve private data generation by reducing feature count.
problem Infinite-dimensional features in kernel mean embedding are impractical for private data generation.
method Replace random features with Hermite polynomial features, leveraging their ordered nature.
result Hermite polynomial features yield a more accurate approximation of kernel mean embedding with fewer features.
New model improves privacy and accuracy by balancing reconstruction error and classification accuracy.
problem Balancing privacy and utility in machine learning models.
method Adversarial learning to find a sweet tradeoff between privacy and utility.
result RAN model achieves better privacy with better utility than existing alternatives.
Dynamic model considers private asset markets' complexities.
problem Understanding and optimizing private asset allocation.
method State-of-the-art dynamic model with machine learning.
result Optimal investment policies quantified over fund life.
Trading floors need to be twice as deep as electronic markets to compete.
problem Informed traders prefer fast electronic markets over slow trading floors.
method Examined the performance of trading floors and electronic markets in a hybrid system.
result Trading floors need to be twice as deep as electronic markets to compete.
This paper reviews methods for feature selection and extraction in pattern analysis.
problem Complex raw data require feature selection or extraction for better discrimination or representation.
method Reviews different methods of feature selection and extraction.
result Compares various methods of feature selection and extraction.
Paper proposes no-regret algorithms for private GP bandit optimization.
problem Private Gaussian process bandit optimization.
method Combines uniform kernel approximator with random perturbations for differentially private GP bandit algorithms.
result Provable no-regret algorithms for stationary kernel functions in two DP settings.
Model predicts exit of private companies using voting of three classifiers.
problem Predicting the exit of privately held companies from limited data.
method Combines three classifiers (Logistic Regression, Random Forest, SVM) on extracted data.
result Achieves 63% predictive accuracy for Private Equity investors.
Proposes LM3FE for multi-modal feature extraction in image classification.
problem High-dimensional features and multi-modal data challenges.
method Large margin multi-modal multi-task feature extraction (LM3FE) framework.
result LM3FE outperforms single-task feature extraction and multi-modal feature extraction.
Paper improves privacy in SGD with low noise, achieving optimal risk rates.
problem Privacy-preserving machine learning with good performance.
method Differentially private SGD with low-noise analysis.
result Achieves optimal excess risk rates for non-smooth losses.
Paper proposes a method to extract style features from unlabeled data.
problem Extracting fine-grained features like styles from unlabeled data.
method Contrastive conditioned variational autoencoders with mutual information constraints.
result The method efficiently extracts style features from real-world natural image datasets.
New framework provides privacy guarantees for practical federated learning.
problem Inadequate privacy guarantees for federated learning due to restrictive assumptions.
method Fed-α-NormEC, integrating multiple local updates, partial client participation, and standard assumptions. result Provably convergent and differentially private federated learning framework.
StochasticNets learn features faster and as accurately as traditional deep nets.
problem Efficient deep feature learning and extraction in neural networks.
method StochasticNets with sparse connectivity between neurons.
result StochasticNets achieve comparable or better classification accuracy with fewer connections.
Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.
problem Improving acoustic scene classification accuracy.
method Harmonic and percussive source separation, two-stream CNN architecture, bilinear pooling.
result Improved accuracy on DCASE 2019 sub task 1a dataset.
Public pretraining improves private model training even in extreme distribution shift scenarios.
problem Improving private model training accuracy in settings with large distribution shift.
method Empirical evaluation and theoretical explanation of public representations improving private training accuracy.
result Public representations can improve private training accuracy by up to 67% over private training from scratch in settings with large distribution shift.
Develops a computationally tractable differentially private mean estimator called the balloon mean.
problem Robust mean estimation in the presence of outliers and heavy-tailed distributions.
method Iterative clipping procedure over Mahalanobis balls.
result Balloon mean is robust to outliers and outperforms existing estimators in contaminated settings.
Paper proposes mimic learning to share intrusion detection models without private data.
problem Difficulty in obtaining labelled training data for intrusion detection models due to privacy concerns.
method Use of mimic learning to transfer knowledge from a teacher model trained on private data to a student model.
result Student model mimics teacher model without access to private data.
Novel privatization framework for high-dimensional variable selection with differential privacy.
problem High-dimensional controlled variable selection with rigorous FDR control under differential privacy constraints.
method Gaussian Johnson-Lindenstrauss Transformation for privatizing the knockoff matrix.
result The proposed private variable selection procedure maintains statistical power even under strict privacy budgets.
Automatically extracts features from time series data for improved forecasting.
problem Manual feature selection for time series forecasting is inefficient and prone to errors.
method Extracts features from time series using recurrence plots and computer vision algorithms.
result Automatically extracted features lead to highly comparable and sometimes superior forecasting performance.
Differentially private ensemble classifiers adapt to data streams while protecting privacy.
problem Adapting to evolving data characteristics while protecting private information.
method Unbounded ensemble updates, model agnostic approach.
result Outperforms competitors on various privacy, drift, and distribution settings.
Heuristics for solving privacy setting problems in neural networks.
problem Maximin problem in generative adversarial privacy setting.
method Greedy algorithm for linear adversaries and alternately optimizing for CNN adversaries.
result The greedy algorithm performs better as the number of instances increases.
Study shows DNNs often extract redundant features, influenced by network size and activation function.
problem Redundancy in deep neural network features.
method Hierarchical clustering of features based on cosine distances, varying network sizes and activation functions.
result Network size and activation function are key factors in DNN redundancy.
This work explains how maximizing latent correlations across multiple data views helps in identifying shared and private components.
problem Understanding how to identify shared and private components in multiview data.
method An intuitive generative model of multiview data is adopted, and latent correlation maximization is shown to guarantee the extraction of shared components.
result Latent correlation maximization guarantees the extraction of shared components across views and disentangles private information.
Study examines neural networks for feature extraction and their impact on machine learning models.
problem Improving feature extraction for better machine learning model performance.
method Used neural networks to extract features from images and numeric data, then compared these features with SVMs and KNNs.
result Neural network-extracted features significantly enhance SVM and KNN performance in many cases.
Efficiently extracts local features from whole images using CNNs with pooling layers.
problem Efficiently extracting local features from whole images for various tasks.
method A method to compute patch-based local feature descriptors efficiently in presence of pooling and striding layers for whole images at once, applicable to nearly all existing network architectures.
result Our approach significantly speeds up feature extraction from whole images compared to existing methods.
Enhances feature extraction for sequential data using CNN and RNN.
problem Extracting features from sequential data efficiently.
method Integrates recurrent neural networks into convolutional layers for sequential data.
result Improves performance in audio classification tasks.
DPNR preserves privacy of text representations using differential privacy.
problem Privacy leakage in deep learning text representations.
method DPNR uses Differential Privacy to provide formal privacy guarantees and dropout masking for enhanced privacy.
result DPNR reduces privacy leakage without significantly sacrificing main task performance.
Relational Autoencoder improves feature extraction by considering data relationships.
problem Feature extraction from high-dimensional data fails to consider data relationships.
method Proposes a Relation Autoencoder model that considers both features and relationships.
result Considering data relationships generates more robust features with lower error rates.
Enhancing malware detection with icon features.
problem Improving accuracy in detecting malware.
method Extract icon features using summary statistics, HOG, and a convolutional autoencoder. Cluster icons and integrate these clusters into machine learning models.
result Significant increase in malware prediction model accuracy (10%) when icon clusters are used.
New algorithms for set union in differential privacy improve efficiency and accuracy.
problem Efficiently discovering items from private user data in natural language processing.
method Developed algorithms that allow users to contribute items in a dependent fashion, guided by a policy with contractive properties.
result New algorithms significantly outperform existing mechanisms in terms of efficiency and accuracy.
End-to-end model extracts nested terms without extra features.
problem Automatic term extraction for nested terms.
method Deep learning model that predicts conceptual terms within fixed sentence lengths.
result High recall and comparable precision on term extraction task.
Proposes DP-MERF for privacy-preserving synthetic data generation.
problem Privacy-preserving data generation for synthetic datasets.
method Differentially private mean embeddings with random features.
result Achieves better privacy-utility trade-offs than existing methods.
A genetic algorithm-based method extracts features for epilepsy EEG classification.
problem Classifying epileptic EEG signals for accurate diagnosis.
method GAFDS method using genetic algorithm for frequency-domain feature search and optimization.
result GAFDS features improve classification accuracy compared to nonlinear features.
Dilated CNN improves multivariate time series classification.
problem Multivariate time series classification.
method Transformed multivariate time series into image-like style, applied dilated and strided convolutions.
result Automatic features extracted by dilated CNN are as effective as hand-crafted features.
Deep-FExt uses machine learning to improve vessel segmentation and centerline detection in medical images.
problem Improving vessel segmentation and centerline detection in medical images.
method Inception models for feature extraction, multi-scale and multi-layer convolutional operators, fully convolutional networks.
result Deep-FExt outperforms existing schemes with high Dice scores on DRIVE and STARE datasets.
Extends feature selection to GNNs, improving accuracy and feature ranking.
problem Improving feature selection in Graph Neural Networks (GNNs).
method Implemented a feature selection algorithm using Gumbel Softmax for ranking and selecting features in GNNs.
result Selected 225 features out of 1433 for the Cora dataset, improving classification accuracy.