Summary of Link Representation Learning For Probabilistic Travel Time Estimation, by Chen Xu et al.
Link Representation Learning for Probabilistic Travel Time Estimation
by Chen Xu, Qiang Wang, Lijun Sun
First submitted to arxiv on: 8 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Gaussian hierarchical model, ProbTTE, offers a novel approach to modeling trip-level link travel time by incorporating inter-trip and intra-trip correlations. This probabilistic framework leverages sparse GPS trajectories through sub-sampling-based data augmentation, enabling fine-grained gradient backpropagation. By conditioning on completed trips that are spatiotemporally adjacent, ProbTTE provides a probability distribution of the travel time for a queried trip. Compared to state-of-the-art deterministic and probabilistic baselines, ProbTTE demonstrates superior performance on two real-world GPS trajectory datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to estimate how long it takes to get somewhere by car or other vehicle. They want to make this more accurate by looking at what happens on the road when you’re driving, like weather and traffic jams. They use special math called a “Gaussian hierarchical model” to help with this. They also find ways to add more information to their data using GPS tracks, which helps them learn about different parts of the road. This new method is better than what’s already out there, and it could be useful for other things too. |
Keywords
» Artificial intelligence » Backpropagation » Data augmentation » Probability
