Year: 2020
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Georgiev, Dobrik, Liò, Pietro
Institution: University of Cambridge
Language: English
Topic: Graph Theory and Algorithms
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3027326458