MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
[Uczenie maszynowe] Autorzy: ChengAo Shen, Wenchao Yu, Fangyu Wu i 6 więcej
Time series forecasting (TSF) is evolving toward multimodal and agentic settings, yet using foundation models remains uneconomical in resource-constrained scenarios, where compact, specialized forecasters are more desirable. However, lightweight forecasters typically require substantial training data, limiting their use in domains with scarce, slowly accumulated, or privacy-sensitive time series. To address this dilemma, we investigate the challenging problem of few-shot learning for lightweight forecasters. We propose MetaCaster, a meta-harness-optimized multi-agent framework that uses agentic data generation to automatically train specialized lightweight forecasters from only a few examples and textual contexts. Our work highlights a new TSF paradigm in which agents act not as forecasters but as intermediary engineers that prepare efficient, task-specific forecasters for deployment. E…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe