Structured Latent Space Modeling over Multi-Scale Temporal Patches for Multivariate Time Series Forecasting

2026-07-07

AI Summary

为解决多变量时间序列预测中跨时间尺度结构一致性问题，提出M2Patch方法，通过多尺度补丁和两种可微惩罚构建结构化潜在空间。

Abstract

Multivariate time series encode structural patterns that unfold across multiple temporal scales, yet most forecasting backbones treat learned representations as transient byproducts of prediction, leaving the organizational geometry of these patterns underexploited. We introduce M2Patch, a CNN-based forecasting architecture that maps channel-independent multivariate observations into a structured latent space through two complementary differentiable constraints. Multi-scale patching decomposes the input into overlapping temporal granularities; depthwise separable convolutions with progressive dilation extract scale-specific features in linear time; and per-scale learned projections compress these features into a compact latent representation. The latent space is organized by an intra-scale smoothness constraint that enforces temporal continuity between adjacent patches, and an inter-scale alignment constraint, realized through learnable cross-scale mappings, that restores cross-granularity interaction within the channel-independent design, ensuring that all scales encode mutually consistent representations of the underlying dynamics. Experiments on ten real-world benchmarks show that M2Patch achieves 57 best and 34 second-best results across 40 forecasting settings, matching or exceeding representative baselines on most benchmarks while maintaining linear computational complexity and robustness to patch-level input corruption.

Problem

• multivariate time series forecasting
• multi-scale temporal patches
• latent space
• structural consistency
• temporal scales

Innovation

• structured latent space
• multi-scale patching
• depthwise separable CNN
• intra-scale smoothness penalty
• inter-scale alignment penalty