arXiv research

The paper constructs non-trivial cocycles for long embeddings with more than one loop.

Two graph homologies help compute embedding space.

ELM improves neural model embeddings for long-tail learning.

Long spacelike embeddings can be approximated by isometric ones.

New method predicts nonfactuality in LLM responses using semantic isotropy.

Paper addresses hidden faces in configuration space integrals for embeddings.

Existence of balanced embedding proved for complex manifold into infinite-dimensional space.

The paper establishes a new pseudoisotopy result for embedding spaces, leading to computations of homotopy groups of long knots.

The homotopy fiber of the inclusion from the long embedding space to the long immersion space is known to be an iterated based loop space (if the codimension is greater than two). In this paper we deloop the homotopy fiber to obtain the topological Stiefel manifold, combining results of Lashof and of Lees. We also give…

Study shows spherical embedding and immersion components are related to homotopy groups.

We give an overview of how calculus of the embedding functor can be used for the study of long knots and summarize various results connecting the calculus approach to the rational homotopy type of spaces of long knots, collapse of the Vassiliev spectral sequence, Hochschild homology of the Poisson operad, finite type k…

Diffusion means converge to extrinsic means for long times on spheres.

Combines PCA and message passing for better graph node embeddings.

Paper detects non-trivial cycles in embedding spaces using graph integrals.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

COLoKe adapts Koopman embeddings online, reducing overfitting and improving long-term predictions.

Sequence feature embedding is a challenging task due to the unstructuredness of sequence, i.e., arbitrary strings of arbitrary length. Existing methods are efficient in extracting short-term dependencies but typically suffer from computation issues for the long-term. Sequence Graph Transform (SGT), a feature embedding …

This paper gives a partial description of the homotopy type of K, the space of long knots in 3-dimensional Euclidean space. The primary result is the construction of a homotopy equivalence between K and the free little 2-cubes object over the space of prime knots. In proving the freeness result, a close correspondence …

Short-term demand forecasting models commonly combine convolutional and recurrent layers to extract complex spatiotemporal patterns in data. Long-term histories are also used to consider periodicity and seasonality patterns as time series data. In this study, we propose an efficient architecture, Temporal-Guided Networ…

Computes homotopy types of embedding spaces in tight contact 3-manifolds.

Paper uses DMD to embed time in spatiotemporal forecasting.

We show that every finite dimensional Hausdorff (not necessarily paracompact, not necessarily second countable) $C^r$-manifold can be embedded into a weakly complete vector space, i.e. a locally convex topological vector space of the form ${\mathbb R}^I$ for an uncountable index set $I$ and determine the minimal cardin…

The article introduces a new set of Polish word embeddings, built using KGR10 corpus, which contains more than 4 billion words. These embeddings are evaluated in the problem of recognition of temporal expressions (timexes) for the Polish language. We described the process of KGR10 corpus creation and a new approach to …

We study piecewise linear co-dimension two embeddings of closed oriented manifolds in Euclidean space, and show that any such embedding can always be isotoped to be a closed braid as long as the ambient dimension is at most five, extending results of Alexander (in ambient dimension three), and Viro and independently Ka…

In this paper we study the Haefliger invariant for long embeddings $\mathbb{R}^{4k-1}\hookrightarrow\mathbb{R}^{6k}$ in terms of the self-intersections of their projections to $\mathbb{R}^{6k-1}$, under the condition that the projection is a generic long immersion $\mathbb{R}^{4k-1}\looparrowright\mathbb{R}^{6k-1}$. We…

Embedding calculus invariants solve knot connectivity and grope cobordism problems.

TSFMs embed non-stationary time series data, revealing specific types of changes.

Forecasting influenza-like illness (ILI) is of prime importance to epidemiologists and health-care providers. Early prediction of epidemic outbreaks plays a pivotal role in disease intervention and control. Most existing work has either limited long-term prediction performance or lacks a comprehensive ability to captur…

We consider the evolution by curvature of a general embedded network with two triple junctions. We classify the possible singularities and we discuss the long time existence of the evolution.

Kernel method estimates long-term effects from short-term data.

Improved molecular property prediction using WL embedding in GNNs.

Many manifold embedding algorithms fail apparently when the data manifold has a large aspect ratio (such as a long, thin strip). Here, we formulate success and failure in terms of finding a smooth embedding, showing also that the problem is pervasive and more complex than previously recognized. Mathematically, success …

Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term recommendation through dimensionality reduction techniques applied to the historical user-item interactions. A recently introduced session-ba…

A novel method extracts topological features from word embeddings for text classification.

We prove that a closed immersed plane curve with total curvature $2πm$ has entropy at least $m$ times the entropy of the embedded circle, as long as it generates a type I singularity under the curve shortening flow (CSF). We construct closed immersed plane curves of total curvature $2πm$ whose entropy is less than $m$ …

Knowledge graph (KG) embedding is well-known in learning representations of KGs. Many models have been proposed to learn the interactions between entities and relations of the triplets. However, long-term information among multiple triplets is also important to KG. In this work, based on the relational paths, which are…

TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for s…

The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we demonstrate, existing recurrent VAE models have difficulty modeling sequences with long-te…

Let X be a smooth subvariety of CP^N. We study a flow, called balancing flow, on the space of projectively equivalent embeddings of X, which attempts to deform the given embedding into a balanced one. If L->X is an ample line bundle, considering embeddings via H^0(L^k) gives a sequence of balancing flows. We prove that…

This paper addresses the data-driven identification of latent dynamical representations of partially-observed systems, i.e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications, including long-term asymptotic patterns. Whereas state-of-the-art data-driven approac…

Gradient flows for knot energies ensure long-term existence of knotted loops.

In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings. We then use a subset of the unlabeled data to fin…

The paper proves infinite-dimensional rational homotopy groups for a specific embedding space.

Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in su…

We will discuss a method for visual presentation of knotted surfaces in the four space, by examining a number and a position of its Morse's critical points. Using this method, we will investigate surface-knot with one critical point of index 1. Then we show infinitely many mutually distinct surface-knots that has an em…

Diffusion maps are an emerging data-driven technique for non-linear dimensionality reduction, which are especially useful for the analysis of coherent structures and nonlinear embeddings of dynamical systems. However, the computational complexity of the diffusion maps algorithm scales with the number of observations. T…

One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we…

Embeds skein algebras into quantum tori using Dehn-Thurston coordinates.