针对缺失数据的不规则时间序列，提出潜空间注意力机制提升预测性能。
SDE-Attention: Latent Attention in SDE-RNNs for Irregularly Sampled Time Series with Missing Data
- 在SDE-RNN潜空间引入通道级注意力，支持动态特征加权与多尺度建模。
- 在30%~90%缺失率下，平均准确率提升4~10个百分点，最高达7%增益。
- 适用于医疗、传感器等缺失数据场景，尤其适合结构各异的时间序列任务。
包含大量缺失观测的不规则时间序列在医疗和传感器网络中十分常见。本文提出SDE-Attention，一种配备潜空间通道级注意力的SDE-RNN家族，包括通道重校准、时变特征注意力和金字塔多尺度自注意力。我们在合成周期数据集和真实世界基准上进行对比实验，评估不同缺失率下的表现。潜空间注意力始终优于基础SDE-RNN。在单变量UCR数据集上，基于LSTM的时变特征模型SDE-TVF-L表现最佳，在30%、60%和90%缺失率下，平均准确率分别比基线提升约4、6和10个百分点（跨数据集平均）。在多变量UEA基准上，引入注意力的模型再次超越基线，SDE-TVF-L在高缺失率下最高实现7%的平均准确率增益。在所提机制中，时变特征注意力在单变量数据上最稳健；而在多变量数据上，不同注意力类型在不同任务上表现优异，表明SDE-Attention可灵活适配各类问题结构。
原文摘要 · Abstract (English)
Irregularly sampled time series with substantial missing observations are common in healthcare and sensor networks. We introduce SDE-Attention, a family of SDE-RNNs equipped with channel-level attention on the latent pre-RNN state, including channel recalibration, time-varying feature attention, and pyramidal multi-scale self-attention. We therefore conduct a comparison on a synthetic periodic dataset and real-world benchmarks, under varying missing rate. Latent-space attention consistently improves over a vanilla SDE-RNN. On the univariate UCR datasets, the LSTM-based time-varying feature model SDE-TVF-L achieves the highest average accuracy, raising mean performance by approximately 4, 6, and 10 percentage points over the baseline at 30%, 60% and 90% missingness, respectively (averaged across datasets). On multivariate UEA benchmarks, attention-augmented models again outperform the backbone, with SDE-TVF-L yielding up to a 7% gain in mean accuracy under high missingness. Among the proposed mechanisms, time-varying feature attention is the most robust on univariate datasets. On multivariate datasets, different attention types excel on different tasks, showing that SDE-Attention can be flexibly adapted to the structure of each problem.
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。