Research map / Graph learning / Knowledge and temporal graphs
When Will You Arrive? Estimating Travel Time Based on Deep 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 |
|---|---|---|---|
| DeepTTE vs RnnTTE (add Geo-Conv, attention, multi-task) | travel time estimation · Chengdu | MAPE: 15.65 -> 11.89 | Helped |
| add Geo-Conv layer (ablation) | DeepTTE · Chengdu / Beijing | MAPE: 13.14 -> 11.89; 12.68 -> 10.92 | Helped |
| increase Geo-Conv kernel size from 3 to 4-6 (ablation) | DeepTTE · Beijing | MAPE: 10.92 -> 11.18/11.31/11.38 | Hurt |
| attention instead of mean pooling (ablation) | DeepTTE · Chengdu / Beijing | MAPE: 12.09 -> 11.89; 11.11 -> 10.92 | Helped |
| add weatherID attribute (ablation) | DeepTTE · Beijing | MAPE: 1.09% | Helped |
| add weekID attribute (ablation) | DeepTTE · Beijing | MAPE: 0.77% | Helped |
| add driverID attribute (ablation) | DeepTTE · Beijing | MAPE: 0.30% | No clear effect |
| multi-task local loss weight beta between 0 and 1 (ablation) | DeepTTE · Chengdu / Beijing | MAPE | Helped |
| add road ID embeddings (ablation) | DeepTTE · Beijing | MAPE: 10.92 -> 10.59 | Helped |
Closest papers by meaning
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting (ICLR 2018 · similarity 0.86)
- DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation (AAAI 2025 · similarity 0.86)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · similarity 0.83)
- Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning (AAAI 2025 · similarity 0.83)
- FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction (ICML 2024 · similarity 0.82)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.82)
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.