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
Towards Foundation Time Series Model: To Synthesize Or Not To Synthesize?
Kseniia Kuvshinova, Olga Tsymboi, Alina Kostromina, Dmitry Simakov, Elizaveta Kovtun
A Data-Driven Two-Phase Multi-Split Causal Ensemble Model for Time Series
Zhipeng Ma, Marco Kemmerling, Daniel Buschmann, Chrismarie Enslin, Daniel Lütticke, Robert H. Schmitt
Motion Code: Robust Time series Classification and Forecasting via Sparse Variational Multi-Stochastic Processes Learning
Chandrajit Bajaj, Minh Nguyen
Multi-scale Spatio-temporal Transformer-based Imbalanced Longitudinal Learning for Glaucoma Forecasting from Irregular Time Series Images
Xikai Yang, Jian Wu, Xi Wang, Yuchen Yuan, Ning Li Wang, Pheng-Ann Heng
Right on Time: Revising Time Series Models by Constraining their Explanations
Maurice Kraus, David Steinmann, Antonia Wüst, Andre Kokozinski, Kristian Kersting
When and How: Learning Identifiable Latent States for Nonstationary Time Series Forecasting
Zijian Li, Ruichu Cai, Zhenhui Yang, Haiqin Huang, Guangyi Chen, Yifan Shen, Zhengming Chen, Xiangchen Song, Kun Zhang