轻量级时序模型TSRM提升预测与补全效果。
TSRM: A Lightweight Temporal Feature Encoding Architecture for Time Series Forecasting and Imputation
- 用CNN分任务学时序模式，再用注意力融合特征
- 在7个基准数据集上表现优于现有方法
- 参数量大幅减少，适合资源受限场景
我们提出一种名为时间序列表示模型（TSRM）的轻量级时序特征编码架构，用于多变量时间序列的预测与补全。该架构基于卷积神经网络（CNN）的表征层，每个层独立完成一项表征学习任务，以捕捉多样化的时序模式，随后通过基于注意力的特征提取层和融合层聚合特征。其设计核心借鉴了Transformer编码器结构，以自注意力机制为核心。在七个标准基准数据集上的实证评估表明，TSRM在预测与补全任务中均优于现有最先进方法，同时显著降低可学习参数数量。代码已开源：https://github.com/RobertLeppich/TSRM。
原文摘要 · Abstract (English)
We introduce a temporal feature encoding architecture called Time Series Representation Model (TSRM) for multivariate time series forecasting and imputation. The architecture is structured around CNN-based representation layers, each dedicated to an independent representation learning task and designed to capture diverse temporal patterns, followed by an attention-based feature extraction layer and a merge layer, designed to aggregate extracted features. The architecture is fundamentally based on a configuration that is inspired by a Transformer encoder, with self-attention mechanisms at its core. The TSRM architecture outperforms state-of-the-art approaches on most of the seven established benchmark datasets considered in our empirical evaluation for both forecasting and imputation tasks. At the same time, it significantly reduces complexity in the form of learnable parameters. The source code is available at https://github.com/RobertLeppich/TSRM.
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。