We introduce SiamTST, a novel representation learning framework for multivariate time series. SiamTST integrates a Siamese network with attention, channel-independent patching, and normalization techniques to achieve superior performance. Evaluated on a real-world industrial telecommunication dataset, SiamTST demonstrates significant improvements in forecasting accuracy over existing methods. Notably, a simple linear network also shows competitive performance, achieving the second-best results, just behind SiamTST. The code is available at https://github.com/simenkristoff/SiamTST.

翻译：本文介绍了SiamTST，一种用于多元时间序列的新型表征学习框架。SiamTST将孪生网络与注意力机制、通道独立分块以及归一化技术相结合，以实现卓越的性能。在真实工业电信数据集上的评估表明，SiamTST在预测精度上相比现有方法有显著提升。值得注意的是，一个简单的线性网络也展现出具有竞争力的性能，取得了仅次于SiamTST的第二佳结果。代码可在 https://github.com/simenkristoff/SiamTST 获取。