Research map / Graph learning / Knowledge and temporal graphs
Congestion Graphs for Automated Time Predictions
Arik Senderovich, J. Christopher Beck, Avigdor Gal, Matthias Weidlich
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 congestion-graph features to XGBoost time prediction | XGBoost · ED time-to-physician, train 5 test 6 | MARE: 0.72 -> 0.70 | Improved |
| add congestion-graph features | XGBoost · ED train 4:10 test 11-12 | MARE: 1.37 -> 1.27 | Improved |
| add congestion-graph features | XGBoost · ED high load 10-12 | MARE: 0.64 -> 0.60 | Improved |
| add congestion-graph features | XGBoost · CC length-of-stay, train 5 test 6 | MARE: 1.26 -> 1.17 | Improved |
| add congestion-graph features | XGBoost · CC high load 9-12 | MARE: 1.34 -> 1.2 | Improved |
| add congestion-graph features | XGBoost · ED, all periods | RMSE (min): 47 -> 45 (train 5) | Improved |
| add congestion-graph features | XGBoost · CC, all periods | RMSE (min): 112 -> 106 (train 5) | Improved |
| use latest-patient wait (Snapshot) predictor instead of long-term average | baseline · ED train 4:10 test 11-12 | MARE: 1.48 -> 1.65 | Hurt |
| longer training with concept drift (entire year) vs summer months | all predictors · ED | RMSE (min): 41 -> 97 (CG) | Hurt |
Closest papers by meaning
- QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers (NeurIPS 2024 · similarity 0.82)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.82)
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.80)
- Spatial-Temporal Heterogenous Graph Contrastive Learning for Microservice Workload Prediction (AAAI 2025 · similarity 0.80)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.79)
- CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery (ICLR 2024 · similarity 0.79)
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.
