# Applying the Neural Bellman-Ford Model to the Single Source Shortest Path Problem

### Spyridon Drakakis, Constantine Kotropoulos

#### 2024

#### Abstract

The Single Source Shortest Path problem aims to compute the shortest paths from a source node to all other nodes on a graph. It is solved using deterministic algorithms such as the Bellman-Ford, Dijkstra’s, and A* algorithms. This paper addresses the shortest path problem using a Message-Passing Neural Network model, the Neural Bellman Ford network, which is modified to conduct Predecessor Prediction. It provides a roadmap for developing models to calculate true optimal paths based on user preferences. Experimental results on real-world maps produced by the Open Street Map package show the ability of a Graph Neural Network to imitate the Bellman-Ford algorithm and solve the Single-Source Shortest Path problem.

Download#### Paper Citation

#### in Harvard Style

Drakakis S. and Kotropoulos C. (2024). **Applying the Neural Bellman-Ford Model to the Single Source Shortest Path Problem**. In *Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM*; ISBN 978-989-758-684-2, SciTePress, pages 386-393. DOI: 10.5220/0012425800003654

#### in Bibtex Style

@conference{icpram24,

author={Spyridon Drakakis and Constantine Kotropoulos},

title={Applying the Neural Bellman-Ford Model to the Single Source Shortest Path Problem},

booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},

year={2024},

pages={386-393},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0012425800003654},

isbn={978-989-758-684-2},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM

TI - Applying the Neural Bellman-Ford Model to the Single Source Shortest Path Problem

SN - 978-989-758-684-2

AU - Drakakis S.

AU - Kotropoulos C.

PY - 2024

SP - 386

EP - 393

DO - 10.5220/0012425800003654

PB - SciTePress