Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behaviour expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architectures impose rigid, fixed-scale structural priors -- such as patch-based tokenization, predefined receptive fields, or frozen backbone encoders -- which can over-regularize temporal dynamics and limit adaptability to abrupt high-magnitude events. To handle this, we introduce the \emph{Multi-scale Temporal Network} (MSTN), a hybrid neural architecture grounded in an \emph{Early Temporal Aggregation} principle. MSTN integrates three complementary components: (i) a multi-scale convolutional encoder that captures fine-grained local structure; (ii) a sequence modeling module that learns long-range dependencies through either recurrent or attention-based mechanisms; and (iii) a self-gated fusion stage incorporating squeeze-excitation and multi-head attention to dynamically modulate cross-scale representations. This design enables MSTN to flexibly model temporal patterns spanning milliseconds to extended horizons, while avoiding the computational burden typically associated with long-context models. Across extensive benchmarks covering forecasting, imputation, classification, and cross-dataset generalization, MSTN consistently delivers state-of-the-art performance, outperforming recent leading approaches including TIME-LLM, HiMTM, SOFTS, LLM4TS, TimesNet, and PatchTST, and establishing new best results on 24 out of 32 datasets. Despite its strong performance, MSTN remains lightweight and supports fast inference, making it well suited for deployment on edge devices and resource-constrained environments.

翻译：现实世界的时间序列通常表现出强烈的非平稳性、复杂的非线性动态特性，以及跨多个时间尺度的行为模式，从快速的局部波动到缓慢演化的长期趋势。然而，许多现代架构采用僵化、固定尺度的结构先验——例如基于分块的标记化、预定义的感受野或冻结的主干编码器——这可能过度正则化时间动态，并限制对突发高强度事件的适应性。为解决这一问题，我们引入了基于“早期时间聚合”原则的混合神经架构——多尺度时间网络（MSTN）。MSTN整合了三个互补组件：（i）一个多尺度卷积编码器，用于捕捉细粒度局部结构；（ii）一个序列建模模块，通过循环或基于注意力的机制学习长程依赖关系；以及（iii）一个融合挤压激励和多头注意力的自门控融合阶段，以动态调制跨尺度表示。这种设计使MSTN能够灵活建模从毫秒到扩展时间范围的时间模式，同时避免通常与长上下文模型相关的计算负担。在涵盖预测、插补、分类和跨数据集泛化的广泛基准测试中，MSTN始终提供最先进的性能，超越了包括TIME-LLM、HiMTM、SOFTS、LLM4TS、TimesNet和PatchTST在内的近期领先方法，并在32个数据集中的24个上建立了新的最佳结果。尽管性能强大，MSTN仍保持轻量级并支持快速推理，使其非常适合在边缘设备和资源受限环境中部署。