Saved in:
Bibliographic Details
Main Authors: Jiang, Yue, Liu, Chenxi, Chen, Yile, Chao, Qin, Liu, Shuai, Long, Cheng, Cong, Gao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.18635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914050220228608
author Jiang, Yue
Liu, Chenxi
Chen, Yile
Chao, Qin
Liu, Shuai
Long, Cheng
Cong, Gao
author_facet Jiang, Yue
Liu, Chenxi
Chen, Yile
Chao, Qin
Liu, Shuai
Long, Cheng
Cong, Gao
contents Urban forecasting models often face a severe data imbalance problem: only a few cities have dense, long-span records, while many others expose short or incomplete histories. Direct transfer from data-rich to data-scarce cities is unreliable because only a limited subset of source patterns truly benefits the target domain, whereas indiscriminate transfer risks introducing noise and negative transfer. We present STRATA-TS (Selective TRAnsfer via TArget-aware retrieval for Time Series), a framework that combines domain-adapted retrieval with reasoning-capable large models to improve forecasting in scarce data regimes. STRATA-TS employs a patch-based temporal encoder to identify source subsequences that are semantically and dynamically aligned with the target query. These retrieved exemplars are then injected into a retrieval-guided reasoning stage, where an LLM performs structured inference over target inputs and retrieved support. To enable efficient deployment, we distill the reasoning process into a compact open model via supervised fine-tuning. Extensive experiments on three parking availability datasets across Singapore, Nottingham, and Glasgow demonstrate that STRATA-TS consistently outperforms strong forecasting and transfer baselines, while providing interpretable knowledge transfer pathways.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning
Jiang, Yue
Liu, Chenxi
Chen, Yile
Chao, Qin
Liu, Shuai
Long, Cheng
Cong, Gao
Machine Learning
Urban forecasting models often face a severe data imbalance problem: only a few cities have dense, long-span records, while many others expose short or incomplete histories. Direct transfer from data-rich to data-scarce cities is unreliable because only a limited subset of source patterns truly benefits the target domain, whereas indiscriminate transfer risks introducing noise and negative transfer. We present STRATA-TS (Selective TRAnsfer via TArget-aware retrieval for Time Series), a framework that combines domain-adapted retrieval with reasoning-capable large models to improve forecasting in scarce data regimes. STRATA-TS employs a patch-based temporal encoder to identify source subsequences that are semantically and dynamically aligned with the target query. These retrieved exemplars are then injected into a retrieval-guided reasoning stage, where an LLM performs structured inference over target inputs and retrieved support. To enable efficient deployment, we distill the reasoning process into a compact open model via supervised fine-tuning. Extensive experiments on three parking availability datasets across Singapore, Nottingham, and Glasgow demonstrate that STRATA-TS consistently outperforms strong forecasting and transfer baselines, while providing interpretable knowledge transfer pathways.
title STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning
topic Machine Learning
url https://arxiv.org/abs/2508.18635