Contrary to the traditional Bag-of-Words approach, we consider the Graph-of-Words (GoW) model in which each document is represented by a graph that encodes relationships between the different terms. Based on this formulation, the importance of a term is determined by weighting the corresponding node in the document, collection and label graphs, using node centrality criteria. We also introduce ...

In this paper we propose a supervised version of the Isomap algorithm by incorporating class label information into a dissimilarity matrix in a financial analysis setting. On the credible assumption that corporates financial status lie on a low dimensional manifold, nonlinear dimensionality reduction based on manifold learning techniques has strong potential for bankruptcy analysis in financial...

We present a method for training multi-label, massively multi-class image classification models, that is faster and more accurate than supervision via a sigmoid cross-entropy loss (logistic regression). Our method consists in embedding high-dimensional sparse labels onto a lower-dimensional dense sphere of unit-normed vectors, and treating the classification problem as a cosine proximity regres...

A novel discriminative supervised neighborhood preserving embedding (DSNPE) method is proposed for feature extraction in classifying hyperspectral remote sensing imagery. DSNPE can preserve the local manifold structure and the neighborhood structure. What’s more, for each data point, DSNPE aims at pulling the neighboring points with the same class label towards it as near as possible, while sim...

So far, various components of image characteristics have been used for steganalysis, including the histogram characteristic function, adjacent colors distribution, and sample pair analysis. However, some certain steganography methods have been proposed that can thwart some analysis approaches through managing the embedding patterns. In this regard, the present paper is intended to introduce a n...

The number of AMPA receptors at synapses depends on receptor cycling. Because receptors diffuse rapidly in plasma membranes, their exocytosis and endocytosis need not occur near synapses. Here, pre-embedding immunogold electron microscopy is applied to dissociated rat hippocampal cultures to provide sensitive, high-resolution snapshots of the distribution of surface AMPA receptors in spines, de...

Understanding how species are distributed across landscapes over time is a fundamental question in biodiversity research. Unfortunately, most species distribution models only target a single species at a time, despite strong ecological evidence that species are not independently distributed. We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple s...

‎For a given measure space $(X,{mathscr B},mu)$ we construct all measure spaces $(Y,{mathscr C},lambda)$ in which $(X,{mathscr B},mu)$ is embeddable‎. ‎The construction is modeled on the ultrafilter construction of the Stone--v{C}ech compactification of a completely regular topological space‎. ‎Under certain conditions the construction simplifies‎. ‎Examples are given when this simplification o...

Given a metric space (X, d), a set of terminals K ⊆ X , and a parameter t ≥ 1, we consider metric structures (e.g., spanners, distance oracles, embedding into normed spaces) that preserve distances for all pairs inK ×X up to a factor of t, and have small size (e.g. number of edges for spanners, dimension for embeddings). While such terminal (aka source-wise) metric structures are known to exist...

Contrastive learning makes it possible to establish similarities between samples by comparing their distances in an intermediate representation space (embedding space) and using loss functions designed attract/repel similar/dissimilar samples. The distance comparison is based exclusively on the sample features. We propose a novel contrastive scheme including labels same embedding as features pe...