Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

69138206275 · Jun 202019922001200920182026
48 results for spatial relations

Model predicts spatial-temporal series with latent dynamical component.

problem Forecasting and discovering spatial-temporal relations in series.
method Recurrent neural network with latent dynamical component and various prior hypotheses.
result Model outperforms baselines in various forecasting tasks.

Link homotopy has been an active area of research for knot theorists since its introduction by Milnor in the 1950s. We introduce a new equivalence relation on spatial graphs called component homotopy, which reduces to link homotopy in the classical case. Unlike previous attempts at generalizing link homotopy to spatial…

2007-04-25abs ↗pdf ↗

Study on spatial graphs and their constituent knots, linking polynomial invariants.

problem Understanding the polynomial invariants of spatial graphs and their constituent knots.
method Analyzing spatial K4K_4 graphs, constructing band surfaces, and relating polynomials.
result Relations between Yamada/Jaeger polynomials and Jones polynomials of constituent knots and associated links.

Defines non-parabolic curves in spatial hybrid space with applications.

problem Defining and analyzing non-parabolic spatial hybrid framed curves.
method Definition and proof of existence and uniqueness theorem for non-parabolic spatial hybrid framed curves.
result Existence and uniqueness theorem for non-parabolic spatial hybrid framed curves.

Graph WaveNet models spatial-temporal graphs by learning hidden dependencies and long sequences.

problem Capturing hidden spatial dependencies and long-range temporal sequences in graphs.
method Graph WaveNet integrates adaptive dependency matrix learning and stacked dilated 1D convolution.
result Graph WaveNet outperforms existing methods on public traffic network datasets.

This article presents a survey of some recent results in the theory of spatial graphs. In particular, we highlight results related to intrinsic knotting and linking and results about symmetries of spatial graphs. In both cases we consider spatial graphs in S3S^3 as well as in other 33-manifolds.

2016-02-25abs ↗pdf ↗

Model predicts severity of traffic accidents using spatial and temporal features.

problem Estimating severity of traffic accidents in aggregated and disaggregated data.
method Gradient Boosting models and Gaussian Processes for inference and feature importance.
result Complexity of road networks and other situational features significantly impact accident severity.

Spatial graphs of non-Eulerian or proper Eulerian planar graphs are unknottable by region crossing changes.

problem Unknottability of spatial graphs by region crossing changes.
method Region crossing changes to switch over/under relations within regions of spatial graph diagrams.
result Spatial graphs of non-Eulerian or proper Eulerian planar graphs are unknottable by region crossing changes.

Proposes DMVST-Net for taxi demand prediction.

problem Improving taxi demand prediction for smart city resource allocation.
method Deep Multi-View Spatial-Temporal Network (DMVST-Net) combining LSTM, CNN, and semantic views.
result Demonstrates effectiveness over state-of-the-art methods on large-scale taxi demand data.

Edge-homotopy and vertex-homotopy are equivalence relations on spatial graphs which are generalizations of Milnor's link-homotopy. We introduce some edge (resp. vertex)-homotopy invariants of spatial graphs by applying the Sato-Levine invariant for the 2-component constituent algebraically split links and show examples…

2005-09-01abs ↗pdf ↗

Hybrid model integrates GATv2 and geostatistics for better spatial prediction and uncertainty.

problem Accurate spatial prediction and uncertainty quantification in epidemiology and risk analysis.
method Integrates Graph Attention Network (GATv2) with model-based geostatistics (MBG) to capture relational and spatial dependencies.
result Hybrid model improves predictive accuracy and uncertainty quantification compared to standalone models.

Edge-homotopy and vertex-homotopy are equivalence relations on spatial graphs which are generalizations of Milnor's link-homotopy. Fleming and the author introduced some edge (resp. vertex)-homotopy invariants of spatial graphs by applying the Sato-Levine invariant for the constituent 2-component algebraically split li…

2007-10-19abs ↗pdf ↗

SpatialSim benchmarks machine learning in recognizing object spatial configurations.

problem Machine learning in recognizing precise geometrical configurations of groups of objects.
method SpatialSim benchmark with tasks of Identification and Comparison, using Graph Neural Networks (MPGNNs).
result MPGNNs outperform baselines in recognizing spatial configurations, highlighting current limits.

Spatial embeddings of planar graphs can have higher unknotting numbers than crossing numbers.

problem Understanding the relationship between unknotting numbers and crossing numbers of spatial embeddings of planar graphs.
method Analyzing specific examples of planar graphs and their spatial embeddings to find counterexamples.
result There exist planar graphs and their spatial embeddings where the unknotting number is greater than half the crossing number.

Models learn spatial templates from implicit language, predicting spatial arrangements with high accuracy.

problem Predicting spatial arrangements from implicit spatial language.
method Simple neural-based models leveraging annotated images and structured text.
result Models can predict spatial arrangements from implicit spatial language with high accuracy, even for unseen objects.

Study on crossing numbers of composite knots and graphs.

problem Understanding the minimal crossing number of composite knots and graphs.
method Relating the minimal crossing number of composite knots to the minimal crossing number of spatial graphs, specifically the 2n-theta curve.
result Proved that for large enough n, the crossing number of the 2n-theta curve is n times the sum of the crossing numbers of the prime knots.

Spatial information is not always necessary for spatio-temporal models.

problem The necessity of including spatial information in spatio-temporal models.
method Comparison of spatial agnostic neural networks with state-of-the-art models on ten datasets.
result Spatial information is not always needed in most spatio-temporal models.

In quantum geometry, we consider a set of loops, a compact orientable surface and a solid compact spatial region, all inside R×R3R4\mathbb{R} \times \mathbb{R}^3 \equiv \mathbb{R}^4, which forms a triple. We want to define an ambient isotopic equivalence relation on such triples, so that we can obtain equivalence invariant…

2017-06-15abs ↗pdf ↗

Study shows how near crushing singularities, Kasner-like regions can exist.

problem Understanding spatial volume densities near crushing singularities.
method Relates existence of Kasner-like regions to asymptotics of spatial volume densities under scale-invariant curvature bounds.
result Kasner-like regions can exist near crushing singularities under certain curvature conditions.

We consider the vacuum Einstein flow with a positive cosmological constant on spatial manifolds of product form. In spatial dimension at least four we show the existence of continuous families of recollapsing models whenever at least one of the factors or admits a Riemannian Einstein metric with positive Einstein const…

2016-08-11abs ↗pdf ↗

Develops BASGCN for graph classification with improved feature learning.

problem Graph classification with information loss and imprecise representation.
method Transforms graphs into grid structures and defines a new spatial graph convolution operation.
result Reduces information loss and improves feature representation compared to existing models.

Language models trained on chess board states outperform those on moves, even with causal masking.

problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.

A new framework combines CNN and GRU for better structural damage detection.

problem Improving damage detection in structural engineering using machine learning.
method Hierarchical CNN and Gated Recurrent Unit (GRU) framework to model spatial and temporal relations.
result The proposed HCG framework significantly outperforms existing methods for structural damage detection.

We extend the theory of combinatorial link Floer homology to a class of oriented spatial graphs called transverse spatial graphs. To do this, we define the notion of a grid diagram representing a transverse spatial graph, which we call a graph grid diagram. We prove that two graph grid diagrams representing the same tr…

2015-06-15abs ↗pdf ↗

STOIC improves energy demand forecasting with reliable uncertainty estimates.

problem Accurate point forecasts alone are insufficient for energy systems; reliable uncertainty estimates are needed.
method Integrates graph-based forecasting with tabular foundation models for zero-shot calibration of spatial-temporal residuals.
result STOIC delivers more reliable and robust uncertainty estimates for complex graph-structured energy time series.

Study on knot properties, showing relation between unknotting and crossing numbers.

problem Relations between unknotting and crossing numbers of spatial embeddings.
method Analyzes handcuff-graphs and theta curves, extends known results to handlebody-knots.
result Characterizes handlebody-knots satisfying the equality between unknotting and crossing numbers.

The study applies spatial density models to mobile node movements using Möbius distributions.

problem Modeling the steady-state density of mobile nodes on a 2D terrain.
method Used mixture density networks with Möbius distributions to describe node density over a disk.
result Möbius distributions are more suitable for capturing radial changes in node density compared to Gaussian distributions.

This work relates the framework of model-based clustering for spatial functional data where the data are surfaces. We first introduce a Bayesian spatial spline regression model with mixed-effects (BSSR) for modeling spatial function data. The BSSR model is based on Nodal basis functions for spatial regression and accom…

2015-08-04abs ↗pdf ↗

A new method classifies hyperspectral images using dynamic graph convolutional networks.

problem Complex spatial context in HSI classification leads to inaccurate results.
method Develops a GCN-based method that captures long-range contextual relations and refines graph edges.
result Significant improvement in HSI classification performance compared to state-of-the-art methods.

Study quantifies risk of extreme wind events using spatial risk measures.

problem Assessing risk of impacts from extreme wind events.
method Spatial risk measure axioms, Brown-Resnick max-stable random fields, powers of max-stable random fields.
result Spatial risk measures associated with extreme wind speeds satisfy risk measure axioms.

Paper proposes a neural network to improve traffic flow forecasting.

problem Forecasting future traffic flow distribution in an area.
method Position-aware convolutional neural network integrating data features and position information.
result Our approach outperforms previous methods even with fewer data sources.