提出新型多尺度时序融合模型，解决变长序列建模难题
Conv-like Scale-Fusion Time Series Transformer: A Multi-Scale Representation for Variable-Length Long Time Series
- 借鉴卷积结构设计时序多尺度融合机制
- 在多个时序尺度上实现特征去冗余与高效融合
- 适合处理长短不一的时序数据，提升预测分类性能
时间序列分析在处理变长数据和实现鲁棒泛化方面面临挑战。尽管基于Transformer的模型已推动时序任务发展，但常存在特征冗余和泛化能力不足的问题。受经典卷积网络金字塔结构启发，我们提出一种基于类卷积多尺度融合变压器的多尺度表征学习框架。该方法引入类似时间卷积的结构，结合补丁操作与多头注意力，实现逐步的时间维度压缩与特征通道扩展。进一步设计了一种新颖的跨尺度注意力机制，有效融合不同时间尺度的特征，并提出对数空间归一化方法以适应变长序列。大量实验表明，该框架在预测与分类任务中优于当前最优方法，具有更强的特征独立性、更低的冗余度。
原文摘要 · Abstract (English)
Time series analysis faces significant challenges in handling variable-length data and achieving robust generalization. While Transformer-based models have advanced time series tasks, they often struggle with feature redundancy and limited generalization capabilities. Drawing inspiration from classical CNN architectures' pyramidal structure, we propose a Multi-Scale Representation Learning Framework based on a Conv-like ScaleFusion Transformer. Our approach introduces a temporal convolution-like structure that combines patching operations with multi-head attention, enabling progressive temporal dimension compression and feature channel expansion. We further develop a novel cross-scale attention mechanism for effective feature fusion across different temporal scales, along with a log-space normalization method for variable-length sequences. Extensive experiments demonstrate that our framework achieves superior feature independence, reduced redundancy, and better performance in forecasting and classification tasks compared to state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。