ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification

Paul Quinlan, Qingguo Li, Xiaodan Zhu|April 9, 2026arXiv

Key Takeaway

ADAPT solves a critical problem in time-series AI: you can now pre-train on many diverse datasets together instead of just one, making it possible to build generalist foundation models that work across different time-series domains.

Summary

This paper introduces ADAPT, a new pre-training method that lets AI models learn from many different time-series datasets simultaneously, even when those datasets have different sizes and structures. By aligning the physical properties of diverse time-series data, the approach enables training a single foundation model on 162 datasets at once—something previous methods couldn't do well.

data scaling

Key Terms

foundation-models self-supervised-pretraining time-series-classification mixed-batch-pretraining