Research map / Graph learning / Graph algorithms and clustering
Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability Using Tree Search and Graph Neural Networks
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 R-TDC tree search instead of PYDC-SMT-ordered DC solving | DTNU controllability solving · Prior-work benchmark | instances solved: TS solves roughly 50% more problem instances; 56% vs 37% | Helped |
| Guide tree search with the MPNN through d-OR depth 15 | TS · Prior-work benchmark | instances solved: +6% | Helped |
| Guide tree search with MPNN | TS · B1 | instances solved: +91% | Helped |
| Guide tree search with MPNN | TS · B2 | instances solved: +980% | Helped |
| Guide tree search with MPNN | TS · B3 | instances solved: +1150% | Helped |
| Use an MPNN with 5 layers rather than shallower or deeper variants (ablation) | MPNN-guided TS · 400 DTNUs with 20–25 controllable timepoints | instances solved | Helped |
| Add residual skip connections (ablation) | MPNN-guided TS · 400 DTNUs with 20–25 controllable timepoints | instances solved | Helped |
| Increase MPNN depth to 8 or more layers rather than 5 layers (ablation) | MPNN-guided TS · 400 DTNUs with 20–25 controllable timepoints | instances solved | Hurt |
| Increase network width for the same depth (ablation) | MPNN-guided TS · 400 DTNUs with 20–25 controllable timepoints | instances solved | Helped |
Closest papers by meaning
- Graph Neural Networks Gone Hogwild (ICLR 2025 · similarity 0.84)
- DNCs Require More Planning Steps (ICML 2024 · similarity 0.83)
- AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs (NeurIPS 2026 · similarity 0.83)
- A Bayesian Approach to Online Planning (ICML 2024 · similarity 0.83)
- Dynamic Latent Routing (NeurIPS 2026 · similarity 0.83)
- TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching (ICML 2025 · 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.