Research map / Time series / Causal and generative time series
Automatic Integration for Spatiotemporal Neural Point Processes
Zihao Zhou, Rose Yu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · COVID-19 NY | LL: 2.1070 ± 0.0342 -> 2.6243 ± 0.5905 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · Earthquake JP | LL: -3.6085 ± 0.0436 -> -3.5948 ± 0.0025 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Hawkes DS2 | LL: -3.2778 -> -2.5304 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Hawkes DS2 | HD: 0.3780 -> 0.1891 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Hawkes DS1 | HD: 0.3198 -> 0.3018 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Hawkes DS3 | HD: 0.2587 -> 0.1495 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Self Correcting DS1 | LL: -1.0317 -> -1.0269 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Self Correcting DS2 | LL: -1.3681 -> -1.3657 | Improved |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Self Correcting DS3 | HD: 0.2334 -> 0.2181 | Hurt |
| Use AutoSTPP instead of Monte Carlo STPP | Neural STPP · ST-Hawkes DS1 | LL: -4.0066 -> -3.9548 | No clear effect |
| Use AutoSTPP instead of DSTPP | Neural STPP · ST-Hawkes DS1 | HD: 0.0033 -> 0.3018 | Hurt |
| Increase the number of summed ProdNets (ablation) | AutoSTPP · Synthetic function fitting | MSE | Improved |
Closest papers by meaning
- Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling (NeurIPS 2026 · similarity 0.89)
- Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process (ICML 2024 · similarity 0.87)
- Interacting Diffusion Processes for Event Sequence Forecasting (ICML 2024 · similarity 0.86)
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.86)
- Neural Jump-Diffusion Temporal Point Processes (ICML 2024 · similarity 0.86)
- ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data (AAAI 2025 · similarity 0.86)
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.
