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.
Combines CNN and LSTM for spatio-temporal graph networks.
Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose…
Enhances SNNs for spatio-temporal feature extraction.
MTRGL learns temporal correlations from multi-modal data for improved pair trading.
Proposes a new model for complex multivariate event data.
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 …
TG-GAN models dynamic graph evolution for continuous-time temporal graphs.
A framework uses deep learning for spatio-temporal data prediction.
TOQ-Nets learn to recognize complex temporal events with varying objects and sequences.
STACI uses neural nets to estimate spatio-temporal fields with valid uncertainty quantification.
Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal clustering into a single end-to-end learning framework, fully unsupe…
Proposes a method to forecast spatial-temporal data with limited training data.
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…
Framework for dynamic node embeddings from graph streams.
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…
Proposes DR-ACI for causal effect intervals with temporal dependence.
FreST Loss decorrelates spatio-temporal dependencies in graph signals.
Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framewo…
Robust spatio-temporal GP framework for outlier-resilient predictions.
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
New neural networks model for spatio-temporal data.
GTEA learns node representations in temporal interaction graphs.
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…
Financial networks have become extremely useful in characterizing the structure of complex financial systems. Meanwhile, the time evolution property of the stock markets can be described by temporal networks. We utilize the temporal network framework to characterize the time-evolving correlation-based networks of stock…
SWoTTeD discovers hidden temporal patterns in EHR data.
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…
TCGPN improves stock forecasting by capturing temporal correlation patterns.
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…
Temporal threat model defends against data poisoning with timestamps.
Kernel for STL formulae enables machine learning in temporal logic.
Model predicts travel time under rare conditions using a vector-space model.
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…
A new method for embedding temporal relationships in graphs.
Within many real-world networks the links between pairs of nodes change over time. Thus, there has been a recent boom in studying temporal graphs. Recognizing patterns in temporal graphs requires a proximity measure to compare different temporal graphs. To this end, we propose to study dynamic time warping on temporal …
New method predicts spatio-temporal data with short and long-range dependence.
Temporal information impacts only a fraction of time series datasets, skewing benchmark evaluations.
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…
TATD predicts missing entries in time-evolving tensors by exploiting temporal dependency and sparsity.
Proposes a non-autoregressive Transformer for time series forecasting.
Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural…
New framework predicts urban traffic with high accuracy.
The paper develops a new model to evaluate policies in complex temporal/spatial experiments.
Flow prediction (e.g., crowd flow, traffic flow) with features of spatial-temporal is increasingly investigated in AI research field. It is very challenging due to the complicated spatial dependencies between different locations and dynamic temporal dependencies among different time intervals. Although measurements of …
HYPA-DBGNN detects anomalous sequential patterns in temporal graphs.
We model GitHub interactions as a temporal knowledge graph for software engineering questions.
Extracting significant places or places of interest (POIs) using individuals' spatio-temporal data is of fundamental importance for human mobility analysis. Classical clustering methods have been used in prior work for detecting POIs, but without considering temporal constraints. Usually, the involved parameters for cl…
LEAP identifies latent causal variables from temporal data.
Evolutionary clustering aims at capturing the temporal evolution of clusters. This issue is particularly important in the context of social media data that are naturally temporally driven. In this paper, we propose a new probabilistic model-based evolutionary clustering technique. The Temporal Multinomial Mixture (TMM)…