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.
New algorithm for RL using mean embeddings of return distributions.
Develops a hybrid deep learning model for stock price prediction.
EHNA learns node embeddings from historical network neighborhoods.
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)---a fully unsupervised node representation learning…
DBGDGM models dynamic brain graphs for better understanding brain function.
Develops a new framework for temporal anchoring in deep embedding spaces.
SARD improves deep learning clinical prediction performance.
Paper tackles class-incremental time series classification with dual-stream feature extraction.
VTD uses deep embeddings to estimate treatment effects from longitudinal data without unconfoundedness assumption.
Paper uses DMD to embed time in spatiotemporal forecasting.
Model integrates multi-view temporal data for better understanding of latent dynamics.
Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately modeling the temporal information, most embedding methods ignore it …
Framework for dynamic node embeddings from graph streams.
A new method for embedding temporal relationships in graphs.
Knowledge Graph (KG) embedding has attracted more attention in recent years. Most KG embedding models learn from time-unaware triples. However, the inclusion of temporal information beside triples would further improve the performance of a KGE model. In this regard, we propose ATiSE, a temporal KG embedding model which…
In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that cre…
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…
In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet) into increasingly fine sub-regions and extract speaker embeddings from each sub-…
Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been proposed to infer new facts for a KG based on the existing ones-a problem known as KG completion. KG embedding approaches have proved effective fo…
The widespread availability of electronic health records (EHRs) promises to usher in the era of personalized medicine. However, the problem of extracting useful clinical representations from longitudinal EHR data remains challenging. In this paper, we explore deep neural network models with learned medical feature embe…
Proposes a graph-based approach for better stock prediction.
Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should repres…
Proposes a new model to predict travel demand with zero-inflated and long-tail characteristics.
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…
Two autoencoding models learn latent traffic scene representations.
MTHetGNN models complex relations in multivariate time series forecasting.
Proposes Deep LTMLE for estimating dynamic treatment effects in longitudinal studies.
Wind power prediction is of vital importance in wind power utilization. There have been a lot of researches based on the time series of the wind power or speed, but In fact, these time series cannot express the temporal and spatial changes of wind, which fundamentally hinders the advance of wind power prediction. In th…
DeepKriging uses neural networks for spatio-temporal interpolation and forecasting.
M2VN forecasts financial volatility by fusing time series data with news embeddings.
Neural Spacetimes learn DAGs by embedding nodes in a spacetime manifold.
EPNE models evolving network patterns for better predictions.
DeepMIDE forecasts wind speeds across space, time, and height for offshore wind energy.
MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.
New method uses neural networks to forecast spatial-temporal data.
New method uses MMAF-guided learning for spatio-temporal probabilistic forecasts.
EEG-TCNet improves MI-BMIs with high accuracy and low resource usage.
We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models. Leveraging recent advances in Stochastic Gradient Variational Bayes, DVBF can overcome intractable inference distributions via variational inference. Thus, it can handle …
In this work, we consider the problem of combining link, content and temporal analysis for community detection and prediction in evolving networks. Such temporal and content-rich networks occur in many real-life settings, such as bibliographic networks and question answering forums. Most of the work in the literature (…
Evaluating the clinical similarities between pairwise patients is a fundamental problem in healthcare informatics. A proper patient similarity measure enables various downstream applications, such as cohort study and treatment comparative effectiveness research. One major carrier for conducting patient similarity resea…
OracleAD detects multivariate time series anomalies without labels.
Identifying mobility behaviors in rich trajectory data is of great economic and social interest to various applications including urban planning, marketing and intelligence. Existing work on trajectory clustering often relies on similarity measurements that utilize raw spatial and/or temporal information of trajectorie…
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 …
Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph…
Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically perceived as a whole. However, although this approach does not require expensive…
A framework uses deep learning for spatio-temporal data prediction.
TG-GAN models dynamic graph evolution for continuous-time temporal graphs.
EPSTE: A geometric token and deep learning approach to estimating transfer entropy in neuroimaging time series