Research map / Probabilistic and scientific modeling / Molecules and proteins
Ordinal Historical Dependence in Graphical Event Models with Tree Representations
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 tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · ICEWS Argentina | log likelihood: -1369 -> -1366 | Helped |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · ICEWS Brazil | log likelihood: -2000 -> -1993 | Helped |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · ICEWS Colombia | log likelihood: -518 -> -518 | No clear effect |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · ICEWS Mexico | log likelihood: -760 -> -766 | Hurt |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · IPTV | log likelihood: -64168 -> -72696 | Hurt |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · LinkedIn | log likelihood: -1462 -> -1406 | Helped |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · Mimic | log likelihood: -474 -> -429 | Helped |
| use tree-shared ordinal intensity parameters instead of the strongest non-tree baseline | OGEM · Stack Overflow | log likelihood: -48323 -> -48232 | Helped |
| replace tree-shared parameters with a tabular parameter for every order instantiation (ablation) | OGEM-tree · Mimic | log likelihood: -429 -> -474 | Hurt |
| learn windows automatically with the heuristic instead of using candidate windows (ablation) | OGEM-tree · ICEWS Argentina | log likelihood: -1366 -> -1393 | Hurt |
| learn windows automatically with the heuristic instead of using candidate windows (ablation) | OGEM-tree · ICEWS Brazil | log likelihood: -2050 -> -1993 | Helped |
| learn windows automatically with the heuristic instead of using candidate windows (ablation) | OGEM-tree · LinkedIn | log likelihood: -1418 -> -1406 | Helped |
Closest papers by meaning
- Proximal Graphical Event Models (NeurIPS 2018 · similarity 0.88)
- MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes (NeurIPS 2026 · similarity 0.86)
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.84)
- Causal Discovery from Event Sequences by Local Cause-Effect Attribution (NeurIPS 2024 · similarity 0.84)
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.83)
- Interacting Diffusion Processes for Event Sequence Forecasting (ICML 2024 · similarity 0.83)
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.