Search Results for author:
Found 4 papers, 1 papers with code
Distinguished In Uniform: Self Attention Vs. Virtual Nodes
We first clarify that this form of universality is not unique to GTs: Using the same positional encodings, also pure MPGNNs and even 2-layer MLPs are non-uniform universal approximators.
Are Targeted Messages More Effective?
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.
Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark
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)
Some Might Say All You Need Is Sum
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.
