no code implementations • 11 Mar 2024 • Martin Grohe, Eran Rosenbluth
In the first version, a message only depends on the state of the source vertex, whereas in the second version it depends on the states of the source and target vertices.
1 code implementation • 1 Sep 2023 • Jan Tönshoff, Martin Ritzert, Eran Rosenbluth, Martin Grohe
The recent Long-Range Graph Benchmark (LRGB, Dwivedi et al. 2022) introduced a set of graph learning tasks strongly dependent on long-range interaction between vertices.
Ranked #1 on Link Prediction on PCQM-Contact (MRR-ext-filtered metric)
no code implementations • 22 Feb 2023 • Eran Rosenbluth, Jan Toenshoff, Martin Grohe
We prove that under certain restrictions, every Mean or Max GNN can be approximated by a Sum GNN, but even there, a combination of (Sum, [Mean/Max]) is more expressive than Sum alone.