# Logistics, Graphs, and Transformers: Towards improving Travel Time Estimation

arXiv: https://arxiv.org/abs/2207.05835 · HTML: https://mlsanity.com/paper/2207.05835/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 8 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 3 of 3)

- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Do Transformers Really Perform Bad for Graph Representation?](https://mlsanity.com/paper/2106.05234/) (2021)
- [Hybrid Graph Embedding Techniques in Estimated Time of Arrival Task](https://mlsanity.com/paper/2110.04228/) (2021)

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

- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [GCT-TTE: Graph Convolutional Transformer for Travel Time Estimation](https://mlsanity.com/paper/2306.04324/) (2023)

## Abstract (arXiv)

The problem of travel time estimation is widely considered as the fundamental challenge of modern logistics. The complex nature of interconnections between spatial aspects of roads and temporal dynamics of ground transport still preserves an area to experiment with. However, the total volume of currently accumulated data encourages the construction of the learning models which have the perspective to significantly outperform earlier solutions. In order to address the problems of travel time estimation, we propose a new method based on transformer architecture - TransTTE.