Research map / Architectures and efficiency / RNNs and normalization
Efficient Learning of Timeseries Shapelets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add DTW alignment preprocessing (ablation) | FLAG · Gun Point | accuracy: 96.7% -> 99.3% | Helped |
| add DTW alignment preprocessing (ablation) | FLAG · PP Little | accuracy: 67.1% -> 72.7% | Helped |
| add DTW alignment preprocessing (ablation) | FLAG · 10 phase-shifted datasets | accuracy: e.g. 69.3% -> 72.2% | Helped |
| use FLAG optimization instead of combinatorial search (IGSVM) | FLAG · Adiac | total time (s): 2510.3 -> 5.9 | Helped |
| use FLAG instead of LTS | FLAG · UCR/UEA 25 datasets | average accuracy rank: 2.0 -> 2.6 | Hurt |
| use FLAG instead of LTS | FLAG · Adiac | total time (s): 61977.0 -> 5.9 | Helped |
| use FLAG instead of SD | FLAG · UCR/UEA 25 datasets | average accuracy rank: 5.9 -> 2.6 | Helped |
| use FLAG instead of UFS random shapelets | FLAG · UCR/UEA 25 datasets | average accuracy rank: 3.7 -> 2.6 | Helped |
| FLAG instead of SD on speed | FLAG · UCR/UEA 25 datasets | average time rank: 1.0 -> 2.0 | Hurt |
| increase N training series in StarlightCurves | FLAG vs SD · StarlightCurves | time | Mixed |
Closest papers by meaning
- Learning Soft Sparse Shapes for Efficient Time-Series Classification (ICML 2025 · similarity 0.89)
- ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models (NeurIPS 2025 · similarity 0.86)
- Diffusion Language-Shapelets for Semi-supervised Time-Series Classification (AAAI 2024 · similarity 0.85)
- Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves (ICML 2025 · similarity 0.84)
- Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification (NeurIPS 2024 · similarity 0.82)
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.