Unsupervised learning with GNNs for QUBO-based combinatorial optimization
Authors:
- Olga KrylovaOKOlga Krylova
- Frank PhillipsonFPFrank Phillipson
Open Access
- 27 September 2025
- journal article
- Published by Elsevier in EURO Journal on Computational Optimization
- Vol. 13
Abstract
No abstract availableFunding Information
- Delta
This publication has 10 references indexed in Scilit:
- Barriers for the performance of graph neural networks (GNN) in discrete random structuresProceedings of the National Academy of Sciences, 2023
- Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent setNature Machine Intelligence, 2022
- Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problemsNature Machine Intelligence, 2022
- Graph coloring with physics-inspired graph neural networksPhysical Review Research, 2022
- Combinatorial optimization with physics-inspired graph neural networksNature Machine Intelligence, 2022
- Understanding the message passing in graph neural networks via power iteration clusteringNeural Networks, 2021
- Learning Combinatorial Optimization on Graphs: A Survey With Applications to NetworkingIEEE Access, 2020
- Message Passing Neural Networks2020
- Quadratic reformulations of nonlinear binary optimization problemsMathematical Programming, 2016
- Approximating maximum independent sets by excluding subgraphsBIT Numerical Mathematics, 1992