arXiv research

Bayesian distance clustering improves robustness to kernel choice.

LOT Wassmap speeds up Wasserstein space manifold learning.

Paper proposes a method to recover point configurations from noisy distance data.

Model tracks structural changes in Brownian particle configurations on a sphere.

Although recovering an Euclidean distance matrix from noisy observations is a common problem in practice, how well this could be done remains largely unknown. To fill in this void, we study a simple distance matrix estimate based upon the so-called regularized kernel estimate. We show that such an estimate can be chara…

New method beats volumetric barrier for manifold recovery.

I-BBS identifies latent sub-manifolds from distance matrices, robust to noise.

Paper proposes new costs for learning multiple centers in MDNs.

As a typical dimensionality reduction technique, random projection can be simply implemented with linear projection, while maintaining the pairwise distances of high-dimensional data with high probability. Considering this technique is mainly exploited for the task of classification, this paper is developed to study th…

Framework uses Minimax distances for unsupervised feature extraction.

Wasserstein t-SNE embeds hierarchical datasets considering within-unit distributions.

Proposes dynamic graph and node feature learning in GCNNs for better adaptability.

In this study, a pairwise comparison matrix is generalized to the case when coefficients create Lie group $G$, non necessarily abelian. A necessary and sufficient criterion for pairwise comparisons matrices to be consistent is provided. Basic criteria for finding a nearest consistent pairwise comparisons matrix (extend…

Low-rank matrix completion has achieved great success in many real-world data applications. A matrix factorization model that learns latent features is usually employed and, to improve prediction performance, the similarities between latent variables can be exploited by pairwise learning using the graph regularized mat…

Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.

Optimized parallel algorithms for identifying strong ties in data.

SWRLDA improves LDA for multi-class classification with edge classes.

Paper introduces differential pairwise privacy for secure metric learning.

New algorithm clusters data and learns kernels without relaxing constraints.

This paper proposes a variant of the method of Guédon and Verhynin for estimating the cluster matrix in the Mixture of Gaussians framework via Semi-Definite Programming. A clustering oriented embedding is deduced from this estimate. The procedure is suitable for very high dimensional data because it is based on pairwis…

The Johnson-Lindenstrauss Lemma allows for the projection of $n$ points in $p-$dimensional Euclidean space onto a $k-$dimensional Euclidean space, with $k \ge \frac{24\ln \emph{n}}{3ε^2-2ε^3}$, so that the pairwise distances are preserved within a factor of $1\pmε$. Here, working directly with the distributions of the …

Study shows attention-style models learn pairwise interactions efficiently.

In this paper we consider the collaborative ranking setting: a pool of users each provides a small number of pairwise preferences between $d$ possible items; from these we need to predict preferences of the users for items they have not yet seen. We do so by fitting a rank $r$ score matrix to the pairwise data, and pro…

Algorithm recovers rankings and synchronizes networks from noisy pairwise measurements.

Extends L2-norm LDA to 2D inputs using Bhattacharyya bound.

Matrix factorization is at the heart of many machine learning algorithms, for example, dimensionality reduction (e.g. kernel PCA) or recommender systems relying on collaborative filtering. Understanding a singular value decomposition (SVD) of a matrix as a neural network optimization problem enables us to decompose lar…

Two-hop walks reveal PageRank order in networks.

Distance metric learning is an important component for many tasks, such as statistical classification and content-based image retrieval. Existing approaches for learning distance metrics from pairwise constraints typically suffer from two major problems. First, most algorithms only offer point estimation of the distanc…

Active seriation recovers item order from noisy pairwise similarity measurements.

A new method for learning row and column structures with missing data.

Many interesting machine learning problems are best posed by considering instances that are distributions, or sample sets drawn from distributions. Previous work devoted to machine learning tasks with distributional inputs has done so through pairwise kernel evaluations between pdfs (or sample sets). While such an appr…

Improved Schizophrenia diagnosis using brain signal features with limited observations.

This study proposes a novel Graph Convolutional Neural Network with Data-driven Graph Filter (GCNN-DDGF) model that can learn hidden heterogeneous pairwise correlations between stations to predict station-level hourly demand in a large-scale bike-sharing network. Two architectures of the GCNN-DDGF model are explored; G…

We consider the problem of estimating undirected triangle-free graphs of high dimensional distributions. Triangle-free graphs form a rich graph family which allows arbitrary loopy structures but 3-cliques. For inferential tractability, we propose a graphical Fermat's principle to regularize the distribution family. Suc…

Enhances clustering performance by integrating tensor similarity.

Stochastic principal component analysis (SPCA) has become a popular dimensionality reduction strategy for large, high-dimensional datasets. We derive a simplified algorithm, called Lazy SPCA, which has reduced computational complexity and is better suited for large-scale distributed computation. We prove that SPCA and …

GCNs' performance linked to feature, graph, and ground truth alignment.

The paper introduces heterogeneous manifolds for better graph embeddings.

EM algorithm converges linearly and achieves sharp rate in estimating mixtures of pairwise differences.

This paper presents a distance-based discriminative framework for learning with probability distributions. Instead of using kernel mean embeddings or generalized radial basis kernels, we introduce embeddings based on dissimilarity of distributions to some reference distributions denoted as templates. Our framework exte…

Estimates parameters of a rectified Gaussian distribution using ReLU networks.

A new k-means variant minimizes pairwise distances within clusters.

Distance-based hierarchical clustering (HC) methods are widely used in unsupervised data analysis but few authors take account of uncertainty in the distance data. We incorporate a statistical model of the uncertainty through corruption or noise in the pairwise distances and investigate the problem of estimating the HC…

MCE reduces embedding instability in nonlinear dimensionality reduction.

Many machine learning problems can be formulated as predicting labels for a pair of objects. Problems of that kind are often referred to as pairwise learning, dyadic prediction or network inference problems. During the last decade kernel methods have played a dominant role in pairwise learning. They still obtain a stat…

In spectral clustering and spectral image segmentation, the data is partioned starting from a given matrix of pairwise similarities S. the matrix S is constructed by hand, or learned on a separate training set. In this paper we show how to achieve spectral clustering in unsupervised mode. Our algorithm starts with a se…

Backpropagation-free RL method trains layers using local signals.

Proposes a new method to learn distance metrics for semi-supervised learning.