Experimental performance of graph neural networks on random instances of max-cut

@inproceedings{Yao2019ExperimentalPO,
  title={Experimental performance of graph neural networks on random instances of max-cut},
  author={Weichi Yao and A. Bandeira and S. Villar},
  booktitle={Optical Engineering + Applications},
  year={2019}
}
  • Weichi Yao, A. Bandeira, S. Villar
  • Published in
    Optical Engineering…
    2019
  • Engineering, Mathematics, Computer Science
  • This note explores the applicability of unsupervised machine learning techniques towards hard optimization problems on random inputs. In particular we consider Graph Neural Networks (GNNs) - a class of neural networks designed to learn functions on graphs - and we apply them to the max-cut problem on random regular graphs. We focus on the max-cut problem on random regular graphs because it is a fundamental problem that has been widely studied. In particular, even though there is no known… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES
    REVISED NOTE ON LEARNING QUADRATIC ASSIGNMENT WITH GRAPH NEURAL NETWORKS
    16
    Extremal Optimization for Graph Partitioning
    130
    Semidefinite programs on sparse random graphs and their application to community detection
    92
    Supervised Community Detection with Line Graph Neural Networks
    82
    The Peculiar Phase Structure of Random Graph Bisection
    10
    Spectral redemption in clustering sparse networks
    433
    The Graph Neural Network Model
    1362
    Gated Graph Sequence Neural Networks
    1042
    Extremal Cuts of Sparse Random Graphs
    55
    Conjecture on the maximum cut and bisection width in random regular graphs
    25