Idioma:

Neural Bipartite Matching

Georgiev, Dobrik ; Liò, Pietro

arXiv.org, 2024-07

Texto completo disponível

Citações Citado por

Título:
Neural Bipartite Matching
Autor: Georgiev, Dobrik ; Liò, Pietro
Assuntos: Algorithms ; Classification ; Computer Science - Learning ; Graph neural networks ; Graph theory ; Machine learning ; Shortest-path problems ; Sorting algorithms ; Statistics - Machine Learning
É parte de: arXiv.org, 2024-07
Descrição: Graph neural networks (GNNs) have found application for learning in the space of algorithms. However, the algorithms chosen by existing research (sorting, Breadth-First search, shortest path finding, etc.) usually align perfectly with a standard GNN architecture. This report describes how neural execution is applied to a complex algorithm, such as finding maximum bipartite matching by reducing it to a flow problem and using Ford-Fulkerson to find the maximum flow. This is achieved via neural execution based only on features generated from a single GNN. The evaluation shows strongly generalising results with the network achieving optimal matching almost 100% of the time.
Editor: Ithaca: Cornell University Library, arXiv.org
Idioma: Inglês

Links

Voltar para lista de resultados

Anterior Resultado 4 Avançar Ir para próxima página