arXiv research

Two new Hie-TAN and Hie-TAN-Lite algorithms improve TAN for hierarchical feature spaces.

Unified framework for modeling hierarchical spaces in design problems.

DHRL learns interpretable features from visual data.

Three-layer networks learn complex hierarchical polynomials of multiple nonlinear features.

DHGAK aligns substructures for better graph kernel performance.

Deep learning explained through spectral filtering of hierarchical features.

There has been a surge in the number of large and flat data sets - data sets containing a large number of features and a relatively small number of observations - due to the growing ability to collect and store information in medical research and other fields. Hierarchical clustering is a widely used clustering tool. I…

Slow feature analysis (SFA) is an unsupervised-learning algorithm that extracts slowly varying features from a multi-dimensional time series. A supervised extension to SFA for classification and regression is graph-based SFA (GSFA). GSFA is based on the preservation of similarities, which are specified by a graph struc…

Deep neural networks have been shown to be very successful at learning feature hierarchies in supervised learning tasks. Generative models, on the other hand, have benefited less from hierarchical models with multiple layers of latent variables. In this paper, we prove that hierarchical latent variable models do not ta…

HGCN uses hyperbolic geometry to improve graph node embeddings.

Extends deep learning for hierarchical data to improve classification accuracy.

The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level categories, which often involves cohesive clustering with a focus on instance relations.…

FISHDBC clusters arbitrary data with flexible, scalable, and hierarchical features.

New algorithm reduces online regression error in RKHS.

Improves few-shot learning for hierarchical data using hyperbolic space.

Paper proposes a new metric learning method for better class separability.

Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a coarse-to-fine hierarchical approach for encoding prior knowledge that drastically …

Method learns hierarchical representations of samples and features simultaneously.

For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depends on the number of observations. This is usually done through the penalization of predictor functions by Euclidean or Hilbertian norms. In …

Extends linear representation hypothesis to categorical and hierarchical concepts in LLMs.

New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.

A new method for linear regression using feature graphs and hierarchical shrinkage.

Paper proposes a method to generate synthetic anomalies for robust anomaly detection.

This paper explains how deep learning performs hierarchical learning efficiently.

In this paper, we propose a Ward-like hierarchical clustering algorithm including spatial/geographical constraints. Two dissimilarity matrices $D_0$ and $D_1$ are inputted, along with a mixing parameter $α\in [0,1]$. The dissimilarities can be non-Euclidean and the weights of the observations can be non-uniform. The fi…

A hierarchical model shows how scaling laws emerge from sequential feature recovery.

Proposes HBGNN for better recommendation systems using graph neural networks.

Improved image reconstruction and anomaly detection using hierarchical VAEs.

A new convolutional spectral kernel network learns hierarchical and local features.

In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters…

Hierarchical VAEs detect out-of-distribution data by identifying low-level in-distribution features.

DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.

Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.

Paper develops a framework for generating coherent image captions using visual features and hierarchical topics.

Proves deep networks can learn hierarchical structures efficiently.

MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.

Paper proposes a GPU-based system for training massive deep learning models in ads systems.

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat m…

We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using the adversarial learning paradigm. We demonstrate that the hierarchical structure supports the learning of progressively more abstract represe…

Deep MF extracts hierarchical features from large data sets.

Machine learning pipeline potentially consists of several stages of operations like data preprocessing, feature engineering and machine learning model training. Each operation has a set of hyper-parameters, which can become irrelevant for the pipeline when the operation is not selected. This gives rise to a hierarchica…

Neural NMF discovers hierarchical topics in multilayer data.

Proposes GPHMEs using Gaussian processes for hierarchical expert models.

CCMM efficiently solves large-scale convex clustering problems.

Proposes a hierarchical clustering method for positive and negative dissimilarities.

Bayesian model estimates feature values of premium products.

Standard Gaussian Process (GP) regression, a powerful machine learning tool, is computationally expensive when it is applied to large datasets, and potentially inaccurate when data points are sparsely distributed in a high-dimensional feature space. To address these challenges, a new multiscale, sparsified GP algorithm…

Boxhead dataset tests autoencoder disentanglement in hierarchical data.