Research map / Probabilistic and scientific modeling / Molecules and proteins
A Variational Point Process Model for Social Event Sequences
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 stochastic latent variable (VAE) to recurrent point process (VEPP vs RMTPP) | VEPP · Retweets | event type log-likelihood: -6.88 -> -6.48 | Helped |
| add stochastic latent variable (VAE) to recurrent point process (VEPP vs RMTPP) | VEPP · MemeTrack | event type log-likelihood: -14.3 -> -10.7 | Helped |
| add latent variable (VEPP vs RMTPP) | VEPP · Retweets | time interval RMSE: 55.42 -> 53.98 | Helped |
| add latent variable (VEPP vs RMTPP) | VEPP · MemeTrack | time interval RMSE: 33.02 -> 32.14 | Helped |
| increase latent size from 32 to 256 (ablation) | VEPP · Retweets | event type log-likelihood: -7.08 -> -6.48 | Helped |
| increase latent size from 256 to 512 (ablation) | VEPP · Retweets | event type log-likelihood: -6.48 -> -6.68 | Hurt |
| increase latent size from 32 to 512 (ablation) | VEPP · MemeTrack | event type log-likelihood: -10.9 -> -10.0 | Helped |
| replace Hawkes process with recurrent neural point process (RMTPP) | RMTPP · MemeTrack | event type log-likelihood: -802.2 -> -14.3 | Helped |
Closest papers by meaning
- Interacting Diffusion Processes for Event Sequence Forecasting (ICML 2024 · similarity 0.89)
- A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs (AAAI 2024 · similarity 0.88)
- A Variational Auto-Encoder Model for Stochastic Point Processes (CVPR 2019 · similarity 0.88)
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.88)
- Deep Continuous-Time State-Space Models for Marked Event Sequences (NeurIPS 2025 · similarity 0.86)
- DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding (NeurIPS 2025 · similarity 0.85)
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.