An hybrid approach based on Graph Attention Network for the Team Orienteering Problem. - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

An hybrid approach based on Graph Attention Network for the Team Orienteering Problem.

Une approche hybride basée sur un réseau d'attention graphique pour le Team Orienteering Problem.

Résumé

We present a Hybrid Graph Attention Model, a learning framework that integrates an efficient splitting algorithm applied to the Team Orienteering Problem (TOP) within a deep learning model. This hybrid approach operates in two steps. Initially, a giant tour (a sequence of customers/locations) is generated at once using a deep neural network. Subsequently, it is evaluated using the split algorithm. The primary objective is to narrow down the solution space in which the deep learning model operates, expecting an overall better performance. Two tailored solution approaches are employed to assess both the performance and the quality of the outcomes. Preliminary findings suggest that our method produces competitive solutions for the TOP.
Fichier principal
Vignette du fichier
An_hybrid_RNN_for_the_TOP.pdf (203.64 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04510551 , version 1 (19-03-2024)

Identifiants

  • HAL Id : hal-04510551 , version 1

Citer

Iván Peña-Arenas, Rym Nesrine Guibadj, Cyril Fonlupt. An hybrid approach based on Graph Attention Network for the Team Orienteering Problem.. OLA 2024 International Conference on Optimization and Learning, Rochester Institute of Technology - RIT, May 2024, Dubrovnik, Croatia. ⟨hal-04510551⟩
0 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More