蒸馏增强的时间序列预测网络与动量对比学习
Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning
AI总结：
提出DE-TSMCL框架，结合可学习数据增强、动量对比学习与监督任务，联合优化多任务损失，有效提升长序列时间序列预测性能，最大改进达27.3%。
摘要：
对比表示学习在时间序列分析中至关重要，因为它缓解了数据噪声、数据不完整以及监督信号稀疏的问题。然而，现有的对比学习框架通常侧重于帧内时间特征，未能充分利用时间序列数据的复杂特性。为解决这一问题，我们提出了DE-TSMCL，一种创新的蒸馏增强框架，用于长序列时间序列预测。具体而言，我们设计了一种可学习的数据增强机制，该机制自适应地学习是否掩盖某个时间戳，以获得优化的子序列。接着，我们提出了一种带有动量更新的对比学习任务，以探索时间序列的样本间和帧内时间相关性，从而在未标记的时间序列上学习潜在的结构特征。同时，我们设计了一个监督任务，以学习更鲁棒的表示并促进对比学习过程。最后，我们联合优化上述两个任务。通过从多个任务中开发模型损失，我们可以为下游预测任务学习有效的表示。与最先进方法相比的大量实验充分证明了DE-TSMCL的有效性，其中最大改进可达27.3%。
英文摘要：
Contrastive representation learning is crucial in time series analysis as it alleviates the issue of data noise and incompleteness as well as sparsity of supervision signal. However, existing constrastive learning frameworks usually focus on intral-temporal features, which fails to fully exploit the intricate nature of time series data. To address this issue, we propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp to obtain optimized sub-sequences. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series to learn the underlying structure feature on the unlabeled time series. Meanwhile, we design a supervised task to learn more robust representations and facilitate the contrastive learning process. Finally, we jointly optimize the above two tasks. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task. Extensive experiments, in comparison with state-of-the-arts, well demonstrate the effectiveness of DE-TSMCL, where the maximum improvement can reach to 27.3%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
