{"ID":2848190,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.26777","arxiv_id":"2510.26777","title":"Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification","abstract":"Recent research on time series foundation models has primarily focused on forecasting, leaving it unclear how generalizable their learned representations are. In this study, we examine whether frozen pre-trained forecasting models can provide effective representations for classification. To this end, we compare different representation extraction strategies and introduce two model-agnostic embedding augmentations. Our experiments show that the best forecasting models achieve classification accuracy that matches or even surpasses that of state-of-the-art models pre-trained specifically for classification. Moreover, we observe a positive correlation between forecasting and classification performance. These findings challenge the assumption that task-specific pre-training is necessary, and suggest that learning to forecast may provide a powerful route toward constructing general-purpose time series foundation models.","short_abstract":"Recent research on time series foundation models has primarily focused on forecasting, leaving it unclear how generalizable their learned representations are. In this study, we examine whether frozen pre-trained forecasting models can provide effective representations for classification. To this end, we compare differe...","url_abs":"https://arxiv.org/abs/2510.26777","url_pdf":"https://arxiv.org/pdf/2510.26777v1","authors":"[\"Andreas Auer\",\"Daniel Klotz\",\"Sebastinan Böck\",\"Sepp Hochreiter\"]","published":"2025-10-30T17:55:23Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}