MASCIT：面向自然不规则时间序列的掩码感知状态空间分类器
MASCIT: A Mask-Aware State Space Classifier for Naturally Irregular Time Series
- Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对自然不规则时间序列，提出掩码感知状态空间分类器MASCIT，通过观测掩码和门控聚合排除无效步骤，在34个数据集上取得最优结果，验证了选择性状态空间模型的有效性。
AI中文摘要：
自然不规则时间序列结合了异步观测、缺失值、不等长度和非均匀采样，而密集适配器可能会丢弃时间结构。我们提出了一种用于不规则时间序列的掩码感知状态空间分类器（MASCIT），该分类器向编码器提供观测掩码，并从门控时间聚合中排除无效步骤。在34个不规则时间序列数据集上，MASCIT取得了最强的聚合点估计，并且是唯一在每一个数据集上都获得三次种子结果的被评估神经模型。在六个重叠的不规则性指标中，MASCIT保持了最低的点排名，而因子消融实验则倾向于部分选择性而非完全选择性。这些结果支持选择性状态空间模型作为自然不规则时间序列分类的有效且可执行的骨干模型。
英文摘要：
Naturally irregular time series combine asynchronous observations, missing values, unequal lengths, and nonuniform sampling, while dense adapters can discard temporal structure. We propose a mask-aware state space classifier for irregular time series (MASCIT), which supplies observation masks to the encoder and excludes invalid steps from gated temporal aggregation. Across 34 irregular time series datasets, MASCIT yielded the strongest aggregate point estimate and was the only evaluated neural model with three-seed results on every dataset. MASCIT retained the lowest point rank across six overlapping irregularity indicators, while factorial ablations favored partial over full selectivity. These results support selective state space models as effective, executable backbones for naturally irregular time series classification.
