arXiv research

Novel neural network solves PDEs with multi-scale resolution.

The analysis of temporal networks has a wide area of applications in a world of technological advances. An important aspect of temporal network analysis is the discovery of community structures. Real data networks are often very large and the communities are observed to have a hierarchical structure referred to as mult…

Temporal Normalizing Flows enhance density estimation of time-dependent data.

We introduce a probabilistic generative model for disentangling spatio-temporal disease trajectories from series of high-dimensional brain images. The model is based on spatio-temporal matrix factorization, where inference on the sources is constrained by anatomically plausible statistical priors. To model realistic tr…

Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences…

Enhances speech emotion recognition by adapting to varying time scales.

Study on eigenvalue distribution of correlated time series, showing deformation of Marchenko-Pastur distribution.

A new deep learning framework captures multi-scale spatio-temporal dependencies.

Efficient spatio-temporal Gaussian process inference method.

STAS selects optimal spatio-temporal scales for bias correction in precipitation forecasts.

MeshfreeFlowNet generates high-resolution spatio-temporal solutions from low-resolution inputs.

The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is s…

Framework for dynamic node embeddings from graph streams.

Temporal aggregation reveals latent default correlation from monthly data.

A new method for reinforcement learning scales errors without tuning.

Temporal coarse-graining of latent default paths explains effective correlation in corporate defaults.

New model scales MHPs for analyzing large-scale diffusion processes.

New framework for analyzing hydroclimatic time series across multiple scales.

Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing…

Taylor's law of temporal fluctuation scaling, variance $\sim$ $a($mean$)^b$, is ubiquitous in natural and social sciences. We report for the first time convincing evidence of a solid temporal fluctuation scaling law in stock illiquidity by investigating the mean-variance relationship of the high-frequency illiquidity o…

Improved weather forecasting with gridded pseudo-token TNPs.

Probabilistic Temporal Tensor Factorization (PTTF) is an effective algorithm to model the temporal tensor data. It leverages a time constraint to capture the evolving properties of tensor data. Nowadays the exploding dataset demands a large scale PTTF analysis, and a parallel solution is critical to accommodate the tre…

Method analyzes large-scale network data to detect communication pattern shifts.

SPF uses a hierarchical approach to efficiently emulate climate changes.

Temporal Causal Prior-Data Fitted Networks (TCPFN) for industrial time series causal discovery

Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex task…

Proposes MSTD-RCNN for improved financial time-series classification.

STACI uses neural nets to estimate spatio-temporal fields with valid uncertainty quantification.

Novel spatio-temporal LSTM model forecasts oceanic variables across sensors and scales.

Variant of mSSA improves time series prediction error.

Event detection has been one of the most important research topics in social media analysis. Most of the traditional approaches detect events based on fixed temporal and spatial resolutions, while in reality events of different scales usually occur simultaneously, namely, they span different intervals in time and space…

Network embedding aims to embed nodes into a low-dimensional space, while capturing the network structures and properties. Although quite a few promising network embedding methods have been proposed, most of them focus on static networks. In fact, temporal networks, which usually evolve over time in terms of microscopi…

Quantum systems with scrambling improve temporal information processing, but scaling requires exponential overhead.

Combines pseudo-point and state space approximations for scalable GPs.

Paper improves multi-step chord prediction in jazz music.

Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The…

The study introduces measures of collective mobility from aggregated OD data.

Networks are a fundamental tool for modeling complex systems in a variety of domains including social and communication networks as well as biology and neuroscience. Small subgraph patterns in networks, called network motifs, are crucial to understanding the structure and function of these systems. However, the role of…

Accurately predicting customer churn using large scale time-series data is a common problem facing many business domains. The creation of model features across various time windows for training and testing can be particularly challenging due to temporal issues common to time-series data. In this paper, we will explore …

Motivated by electricity consumption metering, we extend existing nonnegative matrix factorization (NMF) algorithms to use linear measurements as observations, instead of matrix entries. The objective is to estimate multiple time series at a fine temporal scale from temporal aggregates measured on each individual serie…

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic…

New method improves dynamic topic modeling for large-scale data.

GTEA learns node representations in temporal interaction graphs.

TCR improves DNN robustness to noisy labels with minimal overhead.

This study investigates self-organizing dynamics in a stochastic exponential DAM model using Temporal Complexity.

Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …

We propose the application of a high-speed maximum likelihood clustering algorithm to detect temporal financial market states, using correlation matrices estimated from intraday market microstructure features. We first determine the ex-ante intraday temporal cluster configurations to identify market states, and then st…

Spatio-temporal data and processes are prevalent across a wide variety of scientific disciplines. These processes are often characterized by nonlinear time dynamics that include interactions across multiple scales of spatial and temporal variability. The data sets associated with many of these processes are increasing …