On Size and Hardness Generalization in Unsupervised Learning for the Travelling Salesman Problem

arXiv:2403.20212v1 Announce Type: cross
Abstract: We study the generalization capability of Unsupervised Learning in solving the Travelling Salesman Problem (TSP). We use a Graph Neural Network (GNN) trained with a surrogate loss function to generate an embedding for each node. We use these embeddings to construct a heat map that indicates the likelihood of each edge being part of the optimal route. We then apply local search to generate our final predictions. Our investigation explores how different training instance sizes, …

abstract arxiv capability construct cs.ai cs.lg embedding embeddings function generate gnn graph graph neural network loss network neural network node study type unsupervised unsupervised learning