Research map / Time series / Causal and generative time series
Hierarchical Contrastive Learning for Temporal Point Processes
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 event-level and sequence-level contrastive losses to MLE | HP · Hawkes | Log-Like: -0.06 -> -0.04 | Helped |
| Add event-level and sequence-level contrastive losses to MLE | HP · Missing | Log-Like: -0.06 -> -0.02 | Helped |
| Add event-level and sequence-level contrastive losses to MLE | THP · Retweet | Type-Acc: 0.54 -> 0.56 | Helped |
| Add both event-level and sequence-level contrastive losses instead of using only one (ablation) | MLE+HCL · Synthetic Hawkes | Log-likelihood per event | Helped |
| Add both event-level and sequence-level contrastive losses instead of using only one (ablation) | MLE+HCL · BookOrder | Log-likelihood per event | Helped |
| Use event-level contrastive loss alone, omitting sequence-level contrastive loss (ablation) | MLE+HCL · Synthetic Hawkes and BookOrder | Log-likelihood per event | Hurt |
| Use sequence-level contrastive loss alone, omitting event-level contrastive loss (ablation) | MLE+HCL · Synthetic Hawkes and BookOrder | Log-likelihood per event | Hurt |
Closest papers by meaning
- Noise-Contrastive Estimation for Multivariate Point Processes (NeurIPS 2020 · similarity 0.90)
- Intensity-Free Learning of Temporal Point Processes (ICLR 2020 · similarity 0.88)
- Edit-Based Flow Matching for Temporal Point Processes (ICLR 2026 · 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 0.85)
- A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs (AAAI 2024 · 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.