Time Series Forecasting and Beyond: Efficient Modeling, Structured Learning, and Symbolic Reasoning

ABSTRACT

Time series forecasting has become a central problem in modern machine learning, with applications spanning science, engineering, health, and finance. Yet in many domains, accurate prediction is only the starting point. This talk explores a broader view of time series learning, moving from forecasting toward discovery. I will first discuss our work on efficient time series forecasting, focusing on methods that improve scalability and practicality without sacrificing predictive performance. I will then turn to structured learning for high-dimensional temporal data, showing how modeling dependencies across variables can lead to more reliable and expressive forecasting systems. Finally, I will ask whether machine learning can move beyond forecasting to discover symbolic structure from time series data. I will present our recent work on benchmarking symbolic reasoning over time series and on hybrid LLM-based methods for scientific discovery. These directions point toward time series models that support both prediction and discovery.

BIOGRAPHY

Wei Jin is an Assistant Professor in the Department of Computer Science and the Department of Biostatistics and Bioinformatics at Emory University. His research focuses on time series analysis and AI for health. His honors and achievements include two NIH R01 awards as principal investigator, AAAI New Faculty Highlights, KAUST Rising Stars, the INNS Doctoral Dissertation Runner-up Award, recognition for Most Influential Papers in KDD and WWW by Paper Digest, and top finishes in three NeurIPS competitions. In addition, he has published in leading venues such as PNAS, ICLR, KDD, ICML, NeurIPS, WWW, and AAAI, and has organized multiple tutorials and workshops at several of these conferences.