{"ID":2878034,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18891","arxiv_id":"2508.18891","title":"pyFAST: A Modular PyTorch Framework for Time Series Modeling with Multi-source and Sparse Data","abstract":"Modern time series analysis demands frameworks that are flexible, efficient, and extensible. However, many existing Python libraries exhibit limitations in modularity and in their native support for irregular, multi-source, or sparse data. We introduce pyFAST, a research-oriented PyTorch framework that explicitly decouples data processing from model computation, fostering a cleaner separation of concerns and facilitating rapid experimentation. Its data engine is engineered for complex scenarios, supporting multi-source loading, protein sequence handling, efficient sequence- and patch-level padding, dynamic normalization, and mask-based modeling for both imputation and forecasting. pyFAST integrates LLM-inspired architectures for the alignment-free fusion of sparse data sources and offers native sparse metrics, specialized loss functions, and flexible exogenous data fusion. Training utilities include batch-based streaming aggregation for evaluation and device synergy to maximize computational efficiency. A comprehensive suite of classical and deep learning models (Linears, CNNs, RNNs, Transformers, and GNNs) is provided within a modular architecture that encourages extension. Released under the MIT license at GitHub, pyFAST provides a compact yet powerful platform for advancing time series research and applications.","short_abstract":"Modern time series analysis demands frameworks that are flexible, efficient, and extensible. However, many existing Python libraries exhibit limitations in modularity and in their native support for irregular, multi-source, or sparse data. We introduce pyFAST, a research-oriented PyTorch framework that explicitly decou...","url_abs":"https://arxiv.org/abs/2508.18891","url_pdf":"https://arxiv.org/pdf/2508.18891v1","authors":"[\"Zhijin Wang\",\"Senzhen Wu\",\"Yue Hu\",\"Xiufeng Liu\"]","published":"2025-08-26T10:05:47Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Convolutional Neural Network\",\"Graph Neural Network\"]","has_code":false}