Research map / Time series / Causal and generative time series
Set Functions for Time Series
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 |
|---|---|---|---|
| Use SeFT-Attn instead of GRU-D | M3-Mortality · M3-Mortality | AUPRC: 52.0 \pm 0.8 -> 46.3 \pm 0.5 | Hurt |
| Use SeFT-Attn instead of Transformer | M3-Mortality · M3-Mortality | seconds per epoch: 20.1 \pm 0.1 -> 14.5 \pm 0.5 | Helped |
| Use SeFT-Attn instead of GRU-D | P-Mortality · P-Mortality | AUPRC: 53.7 \pm 0.9 -> 52.4 \pm 1.1 | Hurt |
| Use SeFT-Attn instead of Transformer | P-Mortality · P-Mortality | seconds per epoch: 6.06 \pm 0.06 -> 7.62 \pm 0.10 | Hurt |
| Use SeFT-Attn instead of GRU-Simple | P-Sepsis · P-Sepsis | balanced accuracy: 71.0 \pm 1.4 -> 70.9 \pm 0.8 | No clear effect |
| Mask future information (ablation) | IP-Nets · P-Sepsis | normalized utility: 62.2 \pm 1.3 -> -11.9 \pm 4.0 | Hurt |
| Mask future information (ablation) | Transformer · P-Sepsis | normalized utility: 71.3 \pm 1.4 -> -43.9 \pm 10.0 | Hurt |
| Represent observations as an unordered set and aggregate them independently | SeFT-Attn · M3-Mortality and P-Mortality | seconds per epoch | Mixed |
Closest papers by meaning
- Learning from Irregularly-Sampled Time Series: A Missing Data Perspective (ICML 2020 · similarity 0.85)
- Multi-Time Attention Networks for Irregularly Sampled Time Series (ICLR 2021 · similarity 0.85)
- MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025 · similarity 0.83)
- Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning (AAAI 2025 · similarity 0.83)
- Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting (NeurIPS 2024 · similarity 0.83)
- 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.