AI Paper Atlas

Research map / Time series / Long-term forecasting

Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets

Ziqiang Cheng, Yang Yang, Wei Wang, Wenjie Hu, Yueting Zhuang, Guojie Song

AAAI 2020 · Time series › Long-term forecasting · approach: Spatiotemporal forecasting models · 77 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
Add time-aware shapelets and their learned timing factors (ablation)Time2Graph · EQSaccuracy: 76.98 -> 79.14Improved
Add time-aware shapelets and their learned timing factors (ablation)Time2Graph · WTCaccuracy: 70.13 -> 72.73Improved
Add time-aware shapelets and their learned timing factors (ablation)Time2Graph · STBaccuracy: 95.68 -> 96.76Improved
Add time-aware shapelets and their learned timing factors (ablation)Time2Graph · ECRF1: 31.36 -> 34.44Improved
Add time-aware shapelets and their learned timing factors (ablation)Time2Graph · NTFF1: 42.11 -> 62.97Improved
Replace weighted shapelet assignments with only the highest-probability shapelet per segment, then use LSTM sequence classification (ablation)Time2Graph · EQSaccuracy: 79.14 -> 75.53Hurt
Replace weighted shapelet assignments with only the highest-probability shapelet per segment, then use LSTM sequence classification (ablation)Time2Graph · WTCaccuracy: 72.73 -> 55.84Hurt
Replace weighted shapelet assignments with only the highest-probability shapelet per segment, then use LSTM sequence classification (ablation)Time2Graph · STBaccuracy: 96.76 -> 78.10Hurt
Replace weighted shapelet assignments with only the highest-probability shapelet per segment, then use LSTM sequence classification (ablation)Time2Graph · ECRF1: 34.44 -> 23.66Hurt
Replace weighted shapelet assignments with only the highest-probability shapelet per segment, then use LSTM sequence classification (ablation)Time2Graph · NTFF1: 62.97 -> 28.44Hurt
Use Time2Graph instead of the strongest listed baselineTime series classification · WTCaccuracy: 74.42 -> 72.73Hurt
Use Time2Graph instead of the strongest listed baselineTime series classification · STBaccuracy: 97.03 -> 96.76Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy