{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/primenet-pre-training-for-irregular","title":"PrimeNet: Pre-Training for Irregular Multivariate Time Series","arxiv_id":null,"date":"2023-06-26","proceeding":"AAAI Conference on Artificial Intelligence 2023 6","authors":["Ranak Roy Chowdhury","Jiacheng Li","Xiyuan Zhang","Dezhi Hong","Rajesh K. Gupta","Jingbo Shang"],"abstract":"Real-world applications often involve irregular time series, for which the time intervals between successive observations are non-uniform. Irregularity across multiple features in a multi-variate time series further results in a different subset of features at any given time (i.e., asynchronicity). Existing pre-training schemes for time-series, however, often assume regularity of time series and make no special treatment of irregularity. We argue that such irregularity offers insight about domain property of the data — for example, frequency of hospital visits may signal patient health condition — that can guide representation learning. In this work, we propose PrimeNet to learn a self-supervised representation for irregular multivariate time series. Specifcally, we design a time-sensitive contrastive learning and data reconstruction task to pre-train a model. Irregular time series exhibits considerable variations in sampling density over time. Hence, our triplet generation strategy follows the density of the original data points, preserving its native irregularity. Moreover, the sampling density variation over time makes data reconstruction diffcult for different regions. Therefore, we design a data\r\nmasking technique that always masks a constant time duration to accommodate reconstruction for regions of different sampling density. We learn with these tasks using unlabeled data to build a pre-trained model and fine-tune on a downstream task with limited labeled data, in contrast with existing fully supervised approach for irregular time-series, requiring large amounts of labeled data. Experiment results show that PrimeNet signifcantly outperforms state-of-the-art methods on naturally irregular and asynchronous data from Healthcare and IoT applications for several downstream tasks, including classifcation, interpolation, and regression.","url_abs":"https://ojs.aaai.org/index.php/AAAI/article/view/25876","url_pdf":"https://ojs.aaai.org/index.php/AAAI/article/view/25876/25648","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"primenet-pre-training-for-irregular","repo_url":"https://github.com/ranakroychowdhury/PrimeNet","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"irregular-time-series","task_name":"Irregular Time Series"},{"task_slug":"multivariate-time-series-forecasting","task_name":"Multivariate Time Series Forecasting"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}