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

July 31, 2023

CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
Shohreh Deldari, Dimitris Spathis, Mohammad Malekzadeh, Fahim Kawsar, Flora Salim, Akhil Mathur
Self Supervised Time Series Cross Modal Modality Specific Aware Aggregator Latent Mask

July 30, 2023

Shuffled Differentially Private Federated Learning for Time Series Data Analytics
Chenxi Huang, Chaoyang Jiang, Zhenghua Chen
Time Series Local Differential Privacy Private Federated Learning Privacy Amplification Time Series Datasets Privacy Preserving Federated Learning

July 24, 2023

TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers
Md Fahim Sikder, Resmi Ramachandranpillai, Fredrik Heintz
Diffusion Model Generative Adversarial Network Transformer Megatron Decepticons Time Series Long Sequence Transformer Based Generative Blood Transfusion

July 19, 2023

July 18, 2023

U-shaped Transformer: Retain High Frequency Context in Time Series Analysis
Qingkui Chen, Yiqin Zhang
Time Series Time Series Analysis Long Range Context U Shaped Transformer Backbone Simple MLP

July 17, 2023

Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection
Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen, Wei Xiang
Time Series Temporal Graph Learning Spatial Temporal Graph Multivariate Time Series Anomaly Detection

July 13, 2023

Sequential Monte Carlo Learning for Time Series Structure Discovery
Feras A. Saad, Brian J. Patton, Matthew D. Hoffman, Rif A. Saurous, Vikash K. Mansinghka
Time Series Gaussian Process Posterior Approximation Sequential Monte Carlo Bayesian Nonparametric

July 11, 2023

Enhancing Continuous Time Series Modelling with a Latent ODE-LSTM Approach
C. Coelho, M. Fernanda P. Costa, L. L. Ferrás
Time Series Ordinary Differential Equation

July 7, 2023

July 6, 2023

FITS: Modeling Time Series with $10k$ Parameters
Zhijian Xu, Ailing Zeng, Qiang Xu
Time Series Time Series Forecasting Time Series Data Many Parameter Time Series Analysis Better FiT

June 28, 2023

Autoregressive with Slack Time Series Model for Forecasting a Partially-Observed Dynamical Time Series
Akifumi Okuno, Yuya Morishita, Yoh-ichi Mototake
Time Series Dynamical System Autoregressive Model Time Series Prediction

June 26, 2023

Multivariate Time Series Early Classification Across Channel and Time Dimensions
Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn, Henri Bal
Time Series Edge Intelligence Early Classification Classification Pipeline Temporal Dimension Classification Paradigm

June 23, 2023

June 20, 2023

A Deep Learning Model for Heterogeneous Dataset Analysis -- Application to Winter Wheat Crop Yield Prediction
Yogesh Bansal, David Lillis, Mohand Tahar Kechadi
Deep Learning Model Application Proficiency Time Series Long Short Term Memory Yield Prediction Heterogeneous Datasets Efficient Deep Learning Model

June 16, 2023

June 15, 2023

Deep Learning for Energy Time-Series Analysis and Forecasting
Maria Tzelepi, Charalampos Symeonidis, Paraskevi Nousi, Efstratios Kakaletsis, Theodoros Manousis, Pavlos Tosidis, Nikos Nikolaidis, Anastasios Tefas
Deep Learning Time Series State of the Art Forecasting Load Forecasting Consumption Forecasting Solar Generation

Time Series

Papers

CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking

Shuffled Differentially Private Federated Learning for Time Series Data Analytics

TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers

Forecasting Early with Meta Learning

Sig-Splines: universal approximation and convex calibration of time series generative models

U-shaped Transformer: Retain High Frequency Context in Time Series Analysis

Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection

Sequential Monte Carlo Learning for Time Series Structure Discovery

Enhancing Continuous Time Series Modelling with a Latent ODE-LSTM Approach

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

Personalized Prediction of Recurrent Stress Events Using Self-Supervised Learning on Multimodal Time-Series Data

FITS: Modeling Time Series with $10k$ Parameters

Autoregressive with Slack Time Series Model for Forecasting a Partially-Observed Dynamical Time Series

Multivariate Time Series Early Classification Across Channel and Time Dimensions

On tracking varying bounds when forecasting bounded time series

Higher-order Motif-based Time Series Classification for Forced Oscillation Source Location in Power Grids

A Deep Learning Model for Heterogeneous Dataset Analysis -- Application to Winter Wheat Crop Yield Prediction

MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction

Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects

Deep Learning for Energy Time-Series Analysis and Forecasting