{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:24:47Z","timestamp":1773804287653,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"33","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Pre-trained models have demonstrated exceptional generalization capabilities in time-series forecasting; however, adapting them to evolving data distributions remains a significant challenge. A key hurdle lies in accessing the original training data, as fine-tuning solely on new data often leads to catastrophic forgetting. To address this issue, we propose Replay Tuning (R-Tuning), a novel framework designed for the continual adaptation of pre-trained time-series models.\nR-Tuning constructs a unified latent space that captures both prior and current task knowledge through a frequency-aware replay strategy. Specifically, it augments model-generated samples via wavelet-based decomposition across multiple frequency bands, generating trend-preserving and fusion-enhanced variants to improve representation diversity and replay efficiency. To further reduce reliance on synthetic samples, R-Tuning introduces a latent consistency constraint that aligns new representations with the prior task space. This constraint guides joint optimization within a compact and semantically coherent latent space, ensuring robust knowledge retention and adaptation.\nExtensive experimental results demonstrate the superiority of R-Tuning, which reduces MAE and MSE by up to 46.9% and 46.8%, respectively, on new tasks, while preserving prior knowledge with gains of up to 5.7% and 6.0% on old tasks. Notably, under few-shot settings, R-Tuning outperforms all state-of-the-art baselines even when synthetic proxy samples account for only 5% of the new task dataset.<\/jats:p>","DOI":"10.1609\/aaai.v40i33.40010","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:18:57Z","timestamp":1773800337000},"page":"27870-27878","source":"Crossref","is-referenced-by-count":0,"title":["R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models"],"prefix":"10.1609","volume":"40","author":[{"given":"Tianyi","family":"Yin","sequence":"first","affiliation":[]},{"given":"Jingwei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chenze","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Han","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiexuan","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yunlong","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Yuting","family":"Song","sequence":"additional","affiliation":[]},{"given":"Weiming","family":"Shen","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40010\/43971","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40010\/43971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:18:58Z","timestamp":1773800338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"33","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i33.40010","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}