Picture for J. Kyle Brubaker

J. Kyle Brubaker

Reply to: Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set

Feb 03, 2023
Martin J. A. Schuetz, J. Kyle Brubaker, Helmut G. Katzgraber

* Nature Machine Intelligence 5, 32 (2023)
* Manuscript: 3 pages, 2 figures

Access Paper or Ask Questions

Graph Coloring with Physics-Inspired Graph Neural Networks

Feb 03, 2022
Martin J. A. Schuetz, J. Kyle Brubaker, Zhihuai Zhu, Helmut G. Katzgraber

Figure 1 for Graph Coloring with Physics-Inspired Graph Neural Networks

Figure 2 for Graph Coloring with Physics-Inspired Graph Neural Networks

Figure 3 for Graph Coloring with Physics-Inspired Graph Neural Networks

Figure 4 for Graph Coloring with Physics-Inspired Graph Neural Networks

* Manuscript: 8 pages, 4 figures, 2 tables. Supplemental Material: 1 page, 2 tables

Access Paper or Ask Questions

Combinatorial Optimization with Physics-Inspired Graph Neural Networks

Jul 02, 2021
Martin J. A. Schuetz, J. Kyle Brubaker, Helmut G. Katzgraber

Figure 1 for Combinatorial Optimization with Physics-Inspired Graph Neural Networks

Figure 2 for Combinatorial Optimization with Physics-Inspired Graph Neural Networks

Figure 3 for Combinatorial Optimization with Physics-Inspired Graph Neural Networks

Figure 4 for Combinatorial Optimization with Physics-Inspired Graph Neural Networks

* Manuscript: 13 pages, 5 figures, 1 table. Supplemental Material: 1 page, 1 table

Access Paper or Ask Questions