GRPE-Large

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Graphs2 results

Graph RegressiononPCQM4Mv2-LSC
Test MAE· 2022-01-30
0.0876
best: 0.0683 (EGT + Triangular Attention)
GRPE: Relative Positional Encoding for Graph Transformer arXiv:2201.12787
Graph RegressiononPCQM4Mv2-LSC
Validation MAE· 2022-01-30
0.0867
best: 0.0235 (ESA (Edge set attention, no positional encodings))
GRPE: Relative Positional Encoding for Graph Transformer arXiv:2201.12787