AI 中文总结
该研究提出模型无关的RAEF方法，通过改进检索与聚合机制提升时间序列预测性能，其效果优于RAF，兼具高效性与竞争力，可替代微调用于时间序列预测的领域适配。
AI 中文摘要
基于预训练基础模型的时间序列预测已展现出强大的零样本能力。然而，在领域特定应用中，针对历史数据量少或历史数据可忽略的时间序列实现最优性能，通常需要通过微调或检索增强生成（RAG）进行适配。微调虽有效，但会产生大量计算成本。本研究探索单变量时间序列中的RAG（检索增强生成）作为更高效的替代方案，特别是RAF（检索增强预测），并引入RAEF（检索增强扩展预测），这是一种基于RAF的模型无关方法。RAEF对检索和聚合机制进行了关键改进：（1）在输入空间而非嵌入空间直接检索，降低推理开销；（2）基于连接的聚合方式保留时间结构，而非平均。在多个基准数据集上的实证评估表明，RAEF在准确率和推理开销上均优于RAF。此外，与零样本和微调基础模型的全面对比显示，RAEF实现了与微调相当或更优的性能，同时避免了微调的计算负担，使其成为时间序列预测领域适配的实用且可扩展的方法。
英文摘要
Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time series with short or negligible historical data in domain-specific applications typically requires adaptation via either fine-tuning or RAG. While fine-tuning is effective, it incurs substantial computational costs. This work explores RAG within univariate time series (Retrieval Augmented Generation) as a more efficient alternative, in particular RAF (Retrieval Augmented Forecasting), and introduces RAEF (Retrieval-Augmented Extended Forecasting), a model-agnostic method built upon RAF. RAEF incorporates key refinements to the retrieval and aggregation mechanisms: (1) direct retrieval in input-space rather than embedding-space, reducing inference overhead, and (2) concatenation-based aggregation that preserves temporal structure instead of averaging. Empirical evaluation across multiple benchmark datasets demonstrates that RAEF outperforms RAF in both accuracy and inference overhead. Furthermore, comprehensive comparisons with zero-shot and fine-tuned foundation models show that RAEF achieves competitive or superior performance to fine-tuning while avoiding its computational burden, establishing it as a practical and scalable approach for domain adaptation in time series forecasting.
Comments6 pages, 1 figure
