并非所有检索都有用：时间序列预测中输入感知RAG的交叉注意力
Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
AI总结：
提出Cross-RAG框架，通过查询-检索交叉注意力选择性关注相关检索样本，联合利用查询、检索样本及其关系，提升零样本时间序列预测性能，避免无关检索的干扰。
摘要：
检索增强生成（RAG）通过利用外部知识库增强了零样本时间序列（TS）预测，然而现有方法在将检索样本与查询融合时忽略了输入级别的相关性。我们认为并非所有检索都同样有用，无关的检索会降低性能。为此，我们提出Cross-RAG，一种基于RAG的零样本预测框架，通过查询-检索交叉注意力选择性地关注与查询相关的检索样本。通过建模查询与检索样本之间的输入级别相关性，Cross-RAG联合整合了三种信息源：1）查询本身，2）检索样本，以及3）它们的关系交互。特别地，这种输入感知设计使得Cross-RAG在检索样本数量k增长时保持稳定，而先前没有交叉注意力的方法需要仔细调整k以避免因无关检索导致的性能下降。大量实验表明，Cross-RAG在多个TSFM骨干网络和各种RAG方法上持续提升了零样本预测性能，额外分析证实了其在各种检索场景下的有效性。代码可在该https URL获取。
英文摘要：
Retrieval-augmented generation (RAG) enhances zero-shot time series (TS) forecasting by leveraging external knowledge bases, yet existing approaches overlook input-level relevance when fusing retrieved samples with the query. We argue that not all retrievals are equally useful, and irrelevant ones can degrade performance. To this end, we propose Cross-RAG, a zero-shot RAG-based forecasting framework that selectively attends to query-relevant retrieved samples via query--retrieval cross-attention. By modeling input-level relevance between the query and retrieved samples, Cross-RAG jointly incorporates three sources of information: 1) the query itself, 2) the retrieved samples, and 3) their relational interactions. In particular, this input-aware design enables Cross-RAG to remain stable as the number of retrieved samples $k$ grows, whereas prior methods without cross-attention require careful $k$ tuning to avoid degradation from irrelevant retrievals. Extensive experiments demonstrate that Cross-RAG consistently improves zero-shot forecasting performance across multiple TSFM backbones and various RAG methods, with additional analyses confirming its effectiveness across various retrieval scenarios. Code is available at https://github.com/seunghan96/cross-rag/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
