发表机构
School of Computing and Data Science, The University of Hong Kong; Innovation Engineering College, Macau University of Science and Technology（香港大学计算与数据科学学院; 澳门科技大学创新工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对多元时间序列预测，提出基于卷积神经网络的M2Patch架构，通过多尺度切片、深度可分离卷积等提取特征并压缩成潜表示，利用尺度内和尺度间约束组织潜空间，在多个基准测试中成绩优异。
AI 中文摘要
多元时间序列编码了跨多个时间尺度展开的结构模式，但大多数预测主干将学习到的表示视为预测的临时副产品，未充分利用这些模式的组织几何结构。我们引入了M2Patch，一种基于卷积神经网络的预测架构，通过两个互补的可微约束将与通道无关的多元观测映射到结构化潜空间。多尺度切片将输入分解为重叠的时间粒度；带渐进扩张的深度可分离卷积在线性时间内提取特定尺度特征；每个尺度的学习投影将这些特征压缩成紧凑的潜表示。潜空间由尺度内平滑约束和尺度间对齐约束组织，实验表明M2Patch在多个基准测试中取得了优异成绩。
英文摘要
Existing patching and multi-scale methods advance multivariate time series forecasting but treat learned representations as transient byproducts of prediction, lacking explicit mechanisms that enforce structural consistency across temporal scales. We propose M2Patch, a CNN-based architecture that organizes channel-independent observations into a structured latent space via two complementary differentiable penalties. Multi-scale patching decomposes the input into overlapping temporal granularities, depthwise separable CNN blocks with progressively growing dilation extracts scale-specific features at linear complexity, and per-scale learned projections compress these features into a compact latent representation. An intra-scale smoothness penalty enforces temporal continuity between adjacent patches, while an inter-scale alignment penalty restores cross-granularity interaction through learnable cross-scale mappings, so that all scales encode mutually consistent representations of the underlying dynamics. Extensive experiments on ten real-world benchmark datasets demonstrate that M2Patch significantly outperforms state-of-the-art baselines. Further analyses establish M2Patch as a structure-aware recognizer: it recovers channel functional groupings and remains robust under patch-level input corruption, confirming that the structured latent space captures the data's intrinsic dynamics.
