Research map / Probabilistic and scientific modeling / Molecules and proteins
A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering
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 DMHP instead of MMHP+DPGMM | Event-sequence clustering on sine-like synthetic data (C=5) · Sine-like impact, K=2–5 | clustering purity: 0.5917 -> 0.9898; 0.5565 -> 0.9683; 0.5112 -> 0.9360; 0.4656 -> 0.9055 | Helped |
| Use DMHP instead of MMHP+DPGMM | Event-sequence clustering on piecewise-constant synthetic data (C=5) · Piecewise-constant impact, K=2–5 | clustering purity: 0.5913 -> 0.8085; 0.4517 -> 0.7715; 0.3876 -> 0.7056; 0.3245 -> 0.6774 | Helped |
| Use DMHP instead of MMHP+DPGMM | ICU patient-flow clustering · ICU Patient | clustering consistency: 0.3313 -> 0.3778 | Helped |
| Use DMHP instead of MMHP+DPGMM | IPTV user clustering · IPTV User | clustering consistency: 0.1382 -> 0.2004 | Helped |
| Allocate more inner iterations as outer iterations progress rather than fixing or decreasing the allocation (ablation) | DMHP learning algorithm · Eight synthetic datasets | negative log-likelihood convergence | Helped |
| Use open-loop control to adapt inner-iteration allocation instead of heuristic allocation (ablation) | DMHP learning algorithm · Eight synthetic datasets | negative log-likelihood convergence | Helped |
| Use Bayesian optimization to adapt inner-iteration allocation instead of heuristic allocation (ablation) | DMHP learning algorithm · Eight synthetic datasets | negative log-likelihood convergence | Helped |
| Allocate many inner iterations early rather than updating responsibilities frequently (ablation) | DMHP learning algorithm · Synthetic datasets | responsibility certainty | Hurt |
Closest papers by meaning
- Maximum Margin Dirichlet Process Mixtures for Clustering (AAAI 2016 · similarity 0.89)
- Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic Variables (ICML 2025 · similarity 0.86)
- Meta Learning with Relational Information for Short Sequences (NeurIPS 2019 · similarity 0.86)
- Row-clustering of a Point Process-valued Matrix (NeurIPS 2021 · similarity 0.85)
- Learning Hawkes Processes from Short Doubly-Censored Event Sequences (ICML 2017 · similarity 0.85)
- Learning Mixtures of Gaussian Processes through Random Projection (ICML 2024 · 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.