Time Series

Time series analysis focuses on understanding and modeling data points collected over time, aiming to extract patterns, make predictions, and gain insights from sequential information. Current research emphasizes developing advanced model architectures, such as transformers and recurrent neural networks (RNNs/LSTMs), to handle increasingly complex, high-dimensional, and non-stationary time series data, often incorporating techniques like attention mechanisms and mixture-of-experts models for improved efficiency and accuracy. This field is crucial for numerous applications across diverse domains, including finance, healthcare, and environmental monitoring, enabling better forecasting, anomaly detection, and decision-making based on temporal data.

Papers

October 27, 2023

A Stability Principle for Learning under Non-Stationarity
Chengpiao Huang, Kaizheng Wang
Time Series Statistical Learning Non Stationary Environment Non Stationarity Borkar Meyn Stability Theorem

October 25, 2023

Interpretable time series neural representation for classification purposes
Etienne Le Naour, Ghislain Agoua, Nicolas Baskiotis, Vincent Guigue
Representation Learning Time Series Interpretable Model Neural Representation Symbolic Representation Classification Application

October 18, 2023

Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering
Óscar Jiménez Rama, Fernando Moreno-Pino, David Ramírez, Pablo M. Olmos
Time Series Latent Space Inherent Interpretability Variational Autoencoder Bottleneck Model

October 17, 2023

MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
Chaoyue Ding, Shiliang Sun, Jing Zhao
Time Series Graph Attention Cross Modal Attention Temporal Correlation

October 16, 2023

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook
Ming Jin, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, Xiaoli Li, Shirui Pan, Vincent S. Tseng, Yu Zheng, Lei Chen, Hui Xiong
Timely Survey Time Series Large Model Data Mining Time Series Analysis Temporal Data Outlook Attention

October 15, 2023

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
Xu Liu, Junfeng Hu, Yuan Li, Shizhe Diao, Yuxuan Liang, Bryan Hooi, Roger Zimmermann
Time Series Multivariate Time Series Forecasting Unified Model

October 12, 2023

On Extreme Value Asymptotics of Projected Sample Covariances in High Dimensions with Applications in Finance and Convolutional Networks
Ansgar Steland
Convolutional Neural Network Financial Application Time Series High Dimension High Dimensional Time Series Extreme Value Theory Variance Portfolio Alpha Stable Sample Covariance Matrix

October 11, 2023

October 9, 2023

October 8, 2023

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
Defu Cao, Furong Jia, Sercan O Arik, Tomas Pfister, Yixiang Zheng, Wen Ye, Yan Liu
Time Series Pre Trained Model Time Series Forecasting Generative Pre Trained Transformer Time Series Representation Tempo Estimation Time Series Benchmark Prompt Based Generative

October 6, 2023

T-Rep: Representation Learning for Time Series using Time-Embeddings
Archibald Fraikin, Adrien Bennetot, Stéphanie Allassonnière
Fine Grained Representation Learning Time Series Multivariate Time Series Temporal Feature Temporal Embeddings Time Series Representation

October 5, 2023

October 4, 2023

Graph Neural Networks and Time Series as Directed Graphs for Quality Recognition
Angelica Simonetti, Ferdinando Zanchetta
Graph Neural Network Time Series Recurrent Neural Network Recognition Rate Temporal Convolutional Network Directed Graph Geometric Deep Learning Model Temporal Topological

October 3, 2023

Enhanced LFTSformer: A Novel Long-Term Financial Time Series Prediction Model Using Advanced Feature Engineering and the DS Encoder Informer Architecture
Jianan Zhang, Hongyi Duan
Time Series Financial Time Series Feature Engineering Encoder Architecture Hierarchical Information

Time Series

Papers

A Stability Principle for Learning under Non-Stationarity

Interpretable time series neural representation for classification purposes

Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering

MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting

On Extreme Value Asymptotics of Projected Sample Covariances in High Dimensions with Applications in Finance and Convolutional Networks

Large Language Models Are Zero-Shot Time Series Forecasters

Learning of Sea Surface Height Interpolation from Multi-variate Simulated Satellite Observations

Bidirectional recurrent imputation and abundance estimation of LULC classes with MODIS multispectral time series and geo-topographic and climatic data

NetTiSA: Extended IP Flow with Time-series Features for Universal Bandwidth-constrained High-speed Network Traffic Classification

Deep Optimal Timing Strategies for Time Series

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

T-Rep: Representation Learning for Time Series using Time-Embeddings

An Efficient Content-based Time Series Retrieval System

Toward a Foundation Model for Time Series Data

Comparing Time-Series Analysis Approaches Utilized in Research Papers to Forecast COVID-19 Cases in Africa: A Literature Review

TimeGPT-1

Graph Neural Networks and Time Series as Directed Graphs for Quality Recognition

Enhanced LFTSformer: A Novel Long-Term Financial Time Series Prediction Model Using Advanced Feature Engineering and the DS Encoder Informer Architecture