arXiv：cs.AI· Nguyen Ho, Bach Tung Tran, Trung Ky Nguyen, Zhenchang Xia, Bolong Zheng, Long Van Ho·· 5 小时前AI 评分33
Dual-Stream OSSE-LSTM：标签高效的大规模时间序列分类框架
Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution
AI 导读
研究者提出 Dual-Stream OSSE-LSTM，一种面向少标签场景的 episodic 度量学习框架，将 Omni-Scale CNN 与 Squeeze-and-Excitation 重校准、双向 LSTM 双流融合为原型导向嵌入，并引入 Counterfactual Integrated Gradients（C-IG）实现可解释归因与测试时原型精修。
正文
Abstract:Time series are produced continuously at enormous scale by industrial equipment, wearables, power grids, and clinical monitors, yet annotation remains manual, expensive, and expert-dependent. The binding constraint in large-scale time series analytics is therefore not data volume but label volume, and the question facing a practitioner is concrete: how many examples per class must be labeled before a classifier becomes usable? We study this question directly, in a regime where the label space is fixed and known in advance and the decision rule must be constructed from only K labeled examples per class. We propose Dual-Stream OSSE-LSTM, an episodic metric-learning framework that pairs an Omni-Scale CNN with Squeeze-and-Excitation recalibration, for multi-scale motif extraction without per-dataset kernel tuning, with a Bidirectional LSTM for global temporal context. The two streams are independently normalized and fused into a prototype-oriented embedding. Because decisions taken from a few labels must also be explainable, we introduce Counterfactual Integrated Gradients (C-IG), which attributes the prototype margin between target and opposing classes rather than an isolated classifier logit, and reuses the resulting maps as soft masks for test-time prototype refinement without updating the encoder. On 19 univariate UCR datasets, OSSE-LSTM attains the highest average accuracy and per-dataset win count at every support size, and its accuracy remains within a 0.36-point band (96.36-96.72%) across that range. Its weakest configuration still exceeding the best result any compared baseline achieves at any K (93.99%).
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02704 [cs.AI] |
| (or arXiv:2610.02704v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02704 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nguyen Ho [view email]
[v1]
Fri, 2 Oct 2026 02:40:16 UTC (2,093 KB)
来源：arXiv：cs.AI · arxiv.org