arXiv：cs.LG· Yoo-Min Jung, Hyeon-Gi Kim, Jonghun Park·· 5 小时前AI 评分34
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
AI 导读
MASCIT 是一种掩码感知状态空间分类器，通过向编码器提供观测掩码并在门控时间聚合中排除无效步，处理异步观测、缺失值、不等长和非均匀采样的自然不规则时间序列。在 34 个不规则时间序列数据集上，MASCIT 取得最强聚合点估计，是唯一在每个数据集上都有三随机种子结果的神经模型，并在六项重叠不规则性指标上保持最低点排名。该工作已被 APIEMS 2026 接收。
正文
Abstract: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.
| Comments: | accepted at APIEMS 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.34409 [cs.LG] |
| (or arXiv:2609.34409v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.34409 arXiv-issued DOI via DataCite |
Submission history
From: Yoo-Min Jung [view email]
[v1]
Mon, 28 Sep 2026 06:23:03 UTC (2,277 KB)
[v2]
Fri, 2 Oct 2026 11:58:52 UTC (2,277 KB)
来源：arXiv：cs.LG · arxiv.org