发表机构
Amazon（亚马逊）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究分解组注意力机制，发现均匀池化在多变量和上下文学习预测中普遍有益，而学习权重在上下文学习中常有害，仅统一第一块注意力即可改善所有测试配置。
AI 中文摘要
组注意力由时间序列预测模型Chronos-2引入，在固定的补丁索引处对组的变量进行注意力操作，并同时服务于多变量（MV）和上下文学习（ICL）预测。我们不是整体评估这种跨变量注意力设计，而是探究机制中哪一部分带来了收益，并检验其在MV和ICL两种场景中的适用性。通过在推理时编辑注意力矩阵$\alpha$，我们分离了注意力头所包含的两条路径：V/O，它投影组的加权摘要；以及Q/K，它决定权重。均匀池化（没有Q/K加权的V/O）在我们20个传感器网络配置中的18个上产生正面效果，而学习到的加权（Q/K）则按组类型分化：其对MV的贡献是正面或可忽略的，但在10个传感器网络ICL配置中实质性地损害了8个，其中4个甚至比单变量推理更差。通过隔离不同层的影响，我们发现仅在第一块中统一$\alpha$就能改善我们测试的所有ICL配置。
英文摘要
Group attention, introduced by the time series forecasting model Chronos-2, attends over the variates of a group at a fixed patch index and serves both multivariate (MV) and in-context learning (ICL) forecasting. Rather than evaluating this cross-variate attention design as a whole, we ask which part of the mechanism earns the benefit and probe its applicability to both MV and ICL regimes. By editing the attention matrix $α$ at inference we separate the two pathways a head comprises: V/O, which projects a weighted summary of the group, and Q/K, which decides the weights. Uniform pooling (V/O without any Q/K weighting) is positive on 18 of our 20 sensor-network configurations, while the learned weighting (Q/K) splits by group type: its contribution is positive or negligible for MV, but materially degrades 8 of the 10 sensor-network ICL configurations, leaving 4 of them worse than univariate inference. By isolating the impact of different layers, we find that uniforming $α$ in the first block alone improves every ICL configuration we test.
