Study compares random and learned features in deep Bayesian linear models.
problem Understanding how feature learning affects generalization in deep learning.
method Comparing deep random feature models to deep networks with trained layers.
result Random feature models can display double-descent behavior, while deep networks do not.
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more…
We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows reliable predictors fo…
Feature selection is central to contemporary high-dimensional data analysis. Grouping structure among features arises naturally in various scientific problems. Many methods have been proposed to incorporate the grouping structure information into feature selection. However, these methods are normally restricted to a li…
Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. There are many proposed models in this field such as logistic regression, tree based models, factor…
Deep random feature models are analyzed for their performance with exact asymptotic expressions.
problem Understanding the performance of deep random feature models.
method Established a novel universality result and used the convex Gaussian Min-Max theorem.
result Exact asymptotic expressions for the performance of deep random feature models are derived.
Paper identifies how neural networks learn features.
problem Understanding how neural networks automatically select features.
method Deep Neural Feature Ansatz, implementing average gradient outer product.
result Recursive Feature Machines achieve state-of-the-art performance.
A novel approach combines feature importance scores with deep learning for forex price prediction.
problem Improving forex price prediction using deep learning models.
method Feature importance recap combined with stacking models.
result Proper feature selection significantly improves model performance.
Proposes using gradients as features for efficient deep learning adaptation.
problem Efficient deep representation learning for different tasks.
method Designs a linear model incorporating gradients and activations of a pre-trained network.
result Shows strong results across various tasks and datasets.
Detects out-of-distribution and adversarial samples using deep feature distributions.
problem Detecting out-of-distribution and adversarial samples in deep neural networks.
method Modeling deep features with parametric probability distributions and calculating likelihoods at inference.
result Improves detection of out-of-distribution and adversarial samples, up to 12 percentage points in AUPR and AUROC metrics.
Deep learning models for survival analysis have gained significant attention in the literature, but they suffer from severe performance deficits when the dataset contains many irrelevant features. We give empirical evidence for this problem in real-world medical settings using the state-of-the-art model DeepHit. Furthe…
New adversarial attack method based on deep feature distributions.
problem Adversarial attacks on CNN classifiers using output layer information.
method Modeling and exploiting class-wise and layer-wise deep feature distributions.
result Achieves state-of-the-art transfer-based attack results for undefended ImageNet models.
This paper extends neural collapse to regression problems, revealing key features and structures.
problem Understanding the structure learned by deep neural networks in regression tasks.
method Established Neural Regression Collapse (NRC) across different models, analyzing feature and weight alignments.
result Deep neural regression models exhibit a collapsed feature space, aligning with target dimensions and covariances.
Deep neural networks are a powerful tool for feature learning and extraction given their ability to model high-level abstractions in highly complex data. One area worth exploring in feature learning and extraction using deep neural networks is efficient neural connectivity formation for faster feature learning and extr…
DeepFS uses deep neural networks to select significant features in ultra high-dimensional data.
problem Challenges in traditional feature selection methods for high-dimensional, low-sample-size data.
method Two-step nonparametric approach combining deep neural networks and feature screening.
result DeepFS effectively identifies significant features with high precision for ultra high-dimensional data.
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.
Paper proposes FINN for better CTR prediction by modeling feature interactions.
problem Improving CTR prediction in advertising and recommendation systems.
method Proposes Feature Interaction based Neural Network (FINN) to model feature interactions.
result FINN outperforms other deep models in CTR prediction tasks.
Our paper explains deep neural collapse in multiple layers.
problem Understanding deep neural collapse in multi-layered neural networks.
method Generalized unconstrained features model for deep networks.
result Deep unconstrained features model exhibits deep neural collapse.
ADEC addresses feature randomness and drift in autoencoder-based clustering.
problem Clustering autoencoders learn unreliable pseudo-labels, distorting latent space and feature randomness.
method Adversarial training to balance reconstruction loss and clustering objective.
result ADEC outperforms state-of-the-art autoencoder-based clustering methods.
A unique challenge in predictive model building for omics data has been the small number of samples (n) versus the large amount of features (p). This "n≪p" property brings difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating external gene network info…
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.
We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the m…
We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets | features), the predictive distribution, can be co…
New insights on how weight structure affects generalization in deep Gaussian feature models.
problem Understanding how weight structure impacts generalization in deep learning models.
method Using the replica trick from statistical physics to derive learning curves for models with structured Gaussian features.
result Allowing correlations between the rows of the first layer of features can aid generalization, while structure in later layers is generally detrimental.
Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both width and depth), activation function, and weight initialization on th…
The paper examines the potential of deep learning to support decisions in financial risk management. We develop a deep learning model for predicting whether individual spread traders secure profits from future trades. This task embodies typical modeling challenges faced in risk and behavior forecasting. Conventional ma…
Proposes DAPr framework to learn feature importance from prior knowledge.
problem Ensuring meaningful feature attributions in deep models.
method Jointly learns feature importance from prior knowledge and biases models to rely on important features.
result Improves model generalization and provides new interpretation methods.
Develops deep NMF models using β-divergences for feature extraction.
problem Inadequate evaluation metrics for deep NMF on diverse datasets.
method Introduces new deep NMF models using Kullback-Leibler divergence.
result Improves feature extraction quality across different types of data.
MACQ method explains deep learning models by analyzing feature contributions across prediction levels.
problem Explaining deep learning model predictions.
method Global gradient-based, model-agnostic approach focusing on marginal attribution.
result MACQ separates feature contributions from interaction effects and visualizes 3-way relationships.
PFDL improves deep learning models' OOD generalization by decorrelating feature embeddings.
problem Out-of-distribution generalization in deep learning models.
method PFDL algorithm that optimizes feature decomposition network and image classification model.
result PFDL improves the accuracy of image classification models on OOD datasets.
A new estimator learns sparse linear models with context-dependent coefficients.
problem Sparse linear models lack flexibility compared to deep neural networks for handling feature groups.
method Contextual lasso estimator using a deep neural network with lasso regularization.
result Learned models can be sparser than standard lasso without sacrificing predictive power.
New method deconfounds deep learning feature representations using counterfactual approach.
problem Improving model stability in deep learning models under dataset shifts.
method Adopting last layer features of DNNs trained with softmax activation for logistic regression, and applying counterfactual deconfounding.
result Counterfactual deconfounding can be applied to DNN feature representations, improving model stability.
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs.…
DINs use deep learning to optimize portfolio Sharpe ratio without manual feature engineering.
problem Optimizing Sharpe ratio for entire portfolios without manual feature engineering.
method Fully data-driven feature extraction from daily price returns, balancing turnover and systemic risk.
result DINs outperform traditional TS and CS benchmarks across various asset classes and transaction costs.
Deep MF extracts hierarchical features from large data sets.
problem Mining complex, interleaved features in large data sets.
method Deep matrix factorization models and algorithms.
result Deep MF achieves outstanding performance on unsupervised tasks.
The chapter improves deep learning models by interpreting and improving their performance.
problem Deep learning models often lack interpretability, leading to poor understanding of their predictions.
method The approach involves attributing importance to features and feature groups, including interactions, to improve model performance.
result The proposed attributions provide insights across various domains and can be used to improve model generalization.
Proposes a new method to prevent overfitting in deep neural networks.
problem Overfitting in deep neural networks with many trainable parameters.
method Randomly replaces elements in feature maps with specific values during training.
result Improves the testing performance of deep neural networks on benchmark datasets.
Self-explaining models are models that reveal decision making parameters in an interpretable manner so that the model reasoning process can be directly understood by human beings. General Linear Models (GLMs) are self-explaining because the model weights directly show how each feature contributes to the output value. H…
In this paper, we tackle the real-world problem of predicting Yelp star-review rating based on business features (such as images, descriptions), user features (average previous ratings), and, of particular interest, network properties (which businesses has a user rated before). We compare multiple models on different s…
Adapts IG for better feature attributions and robustness.
problem Reliability concerns in feature attributions for deep learning models.
method Adaptation of path-based feature attribution to Riemannian geometry of data manifolds.
result IG along geodesics generates more intuitive and robust explanations.
Deep learning models misclassify malware with added benign features.
problem Detecting malware with deep learning when it's mixed with benign code.
method Trained a deep neural network classifier using benign and malware features. Demonstrated the impact of adding benign features to malware. Used data augmentation to improve classifier robustness.
result Adding benign features to malware significantly increases false negatives.
Study analyzes feedback complexity for sparse feature retrieval in deep networks.
problem Learning sparse superposed features with feedback.
method Analysis of feedback complexity in sparse settings, including triplet comparisons.
result Establishes tight bounds and strong upper bounds for feature recovery.
Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods have a strong bias towards low- or high-order interactions, or rely on expertise feature engineering. In this paper, we show that it is possible to derive an …
Unified theory explains how data augmentation improves deep learning models.
problem Understanding why data augmentation improves model generalization.
method Unified theoretical framework explaining two key effects: partial semantic feature removal and feature mixing.
result Data augmentation enhances generalization through partial semantic feature removal and feature mixing.
Enhances DGPs with adaptive RKHS Fourier features for better non-stationary pattern modeling.
problem Capturing complex non-stationary patterns in non-linear dynamical systems.
method Integrates ODE-based RKHS Fourier features into DGPs using convolution operations for adaptive amplitude and phase modulation. Uses a doubly stochastic variational inference framework.
result Improved predictive performance across various regression tasks.
Deep learning matches classical feature-based AS models for TSP.
problem Automated selection of algorithms for the TSP.
method Evolved instances, deep neural network, visual representation.
result Deep learning approach matches classical feature-based models.
Deep learning features improve CBIR system performance.
problem Retrieving similar images from a large database.
method Using features from pre-trained deep learning models for similarity retrieval.
result Significantly superior retrieval results compared to traditional methods.
DDLK uses deep learning to find important features in models.
problem Discovering important features in black box models like deep neural networks.
method DDLK directly minimizes KL divergence to generate knockoffs that obey the swap property.
result DDLK outperforms baselines in discovering important features while controlling false discovery rate.