MetaCaster：用于轻量级时间序列预测器小样本端到端学习的元调控优化智能体
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
浏览论文内容
中文总结 AI 辅助
针对资源受限场景下轻量级时间序列预测器小样本学习的困境，提出MetaCaster多智能体框架，可高效训练专用预测器，在18个数据集等实验中兼顾数据、计算效率与预测性能。
中文摘要 AI 辅助
时间序列预测（TSF）正朝着多模态和智能体化场景发展，但在资源受限场景下使用基础模型仍不经济，此时更需要紧凑的专用预测器。然而轻量级预测器通常需要大量训练数据，限制了其在数据稀缺、积累缓慢或隐私敏感的时间序列领域的应用。为解决这一困境，我们研究轻量级预测器的小样本学习这一具有挑战性的问题，提出MetaCaster，这是一种元调控优化的多智能体框架，利用智能体化数据生成仅从少量示例和文本上下文自动训练专用轻量级预测器。本研究提出了一种新的TSF范式，其中智能体并非作为预测器，而是作为中间工程师准备高效的任务专用预测器用于部署。在18个数据集、23个最先进的轻量级预测器和14个基准上的实验表明，MetaCaster在保持高质量TSF性能的同时，实现了数据效率和计算效率。
英文摘要
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. Experiments on 18 datasets, 23 state-of-the-art lightweight forecasters, and 14 baselines demonstrate that MetaCaster achieves both data efficiency and computational efficiency while maintaining high-quality TSF performance.
发表机构
- University of Houston（休斯顿大学）
- NEC Labs（NEC实验室）
- University of Waterloo（滑铁卢大学）
- University of Connecticut（康涅狄格大学）
- University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
- Singapore Management University（新加坡管理大学）
机构由 AI 辅助整理，请以论文原文为准。
