# Hierarchical Graph Structures for Congestion and ETA Prediction

arXiv: https://arxiv.org/abs/2211.11762 · HTML: https://mlsanity.com/paper/2211.11762/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Builds on (most cited first, 2 of 2)

- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes](https://mlsanity.com/paper/2203.17070/) (2022)

## Built on by (most cited first, 2 of 2)

- [Next Level Message-Passing with Hierarchical Support Graphs](https://mlsanity.com/paper/2406.15852/) (2024)
- [Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors](https://mlsanity.com/paper/2303.07758/) (2023)

## Abstract (arXiv)

Traffic4cast is an annual competition to predict spatio temporal traffic based on real world data. We propose an approach using Graph Neural Networks that directly works on the road graph topology which was extracted from OpenStreetMap data. Our architecture can incorporate a hierarchical graph representation to improve the information flow between key intersections of the graph and the shortest paths connecting them. Furthermore, we investigate how the road graph can be compacted to ease the flow of information and make use of a multi-task approach to predict congestion classes and ETA simultaneously. Our code and models are released here: https://github.com/floriangroetschla/NeurIPS2022-traffic4cast