Research map / Federated learning and privacy / Privacy attacks and secure learning
Traffic Updates: Saying a Lot While Revealing a Little
John Krumm, Eric Horvitz
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 |
|---|---|---|---|
| increase vehicles reporting per station (1 to 20) (ablation) | MRF traffic inference · PeMS LA | RMS speed error | Improved |
| increase vehicles per station beyond about 20 (ablation) | MRF traffic inference · PeMS LA | RMS speed error | No clear effect |
| increase number of reporting stations (ablation) | MRF traffic inference · PeMS LA | RMS speed error | Improved |
| self-select reporting vehicles probabilistically without communication | deterministic coordination · PeMS LA | RMS speed error | No clear effect |
| report in descending order of estimated VOI instead of random order | MRF traffic inference · PeMS LA | RMS speed error | Improved |
| VOI ordering vs random ordering (n=1) | station selection · PeMS LA | station reports saved: 17.4 average, up to 23 | Improved |
| use only n=20 vehicles per station at M=109 stations | MRF traffic inference · PeMS LA | number of reports: 26, 204 -> 0.083 of reports | Improved |
| filter reports with VOI below threshold | VOI inference · PeMS LA | classification accuracy: 0.965 | Improved |
Closest papers by meaning
- On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance (NeurIPS 2024 · similarity 0.82)
- TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents (NeurIPS 2025 · similarity 0.81)
- Decomposed Spatio-Temporal Mamba for Long-Term Traffic Prediction (AAAI 2025 · similarity 0.81)
- FairTP: A Prolonged Fairness Framework for Traffic Prediction (AAAI 2025 · similarity 0.81)
- PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models (NeurIPS 2025 · similarity 0.80)
- Trajeglish: Traffic Modeling as Next-Token Prediction (ICLR 2024 · similarity 0.80)
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.
