Research map / Time series / Causal and generative time series
METP: Multi-Granularity Integration of External Covariates for Temporal Point Processes
Boyang Li, Lingzheng Zhang, Fugee Tsung, Xi Zhang
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 |
|---|---|---|---|
| add external covariates (ablation) | METP · GTD | NLL: 9.56 -> 8.25 | Improved |
| add external covariates (ablation) | METP · Tianchi | NMAE: 1.56 -> 0.98 | Improved |
| add lagged weights (ablation) | METP · GTD | NLL: 8.96 -> 8.25 | Improved |
| add lagged weights (ablation) | METP · Tianchi | NMAE: 1.25 -> 0.98 | Improved |
| add multi-scale structure (ablation) | METP · GTD | NLL: 8.31 -> 8.25 | Improved |
| add multi-scale structure (ablation) | METP · Tianchi | NRMSE: 3.32 -> 3.15 | Improved |
| add periodic structure (ablation) | METP · GTD | NLL: 8.65 -> 8.25 | Improved |
| add periodic structure (ablation) | METP · Tianchi | NRMSE: 3.30 -> 3.15 | Improved |
| use METP instead of RMTPP | RMTPP · Tianchi | NMAE: 0.58 -> 0.98 | Hurt |
| use METP instead of ITHP | ITHP · Earthquake | NRMSE: NLL 10.86 -> 10.06; NRMSE 8.77 -> 8.91 | Mixed |
Closest papers by meaning
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.86)
- TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization (NeurIPS 2026 · similarity 0.85)
- Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling (NeurIPS 2026 · similarity 0.84)
- Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment (NeurIPS 2024 · similarity 0.84)
- GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting (AAAI 2024 · similarity 0.84)
- MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes (NeurIPS 2026 · similarity 0.84)
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.
