GPTrans-L

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Graphs3 results

Graph RegressiononPCQM4M-LSC
Validation MAE· 2023-05-19
0.1151
best: 0.1148 (O-GNN)
SOTA
Graph Propagation Transformer for Graph Representation Learning arXiv:2305.11424
Graph RegressiononPCQM4Mv2-LSC
Test MAE· 2023-05-19
0.0821
best: 0.0683 (EGT + Triangular Attention)
Graph Propagation Transformer for Graph Representation Learning arXiv:2305.11424
Graph RegressiononPCQM4Mv2-LSC
Validation MAE· 2023-05-19
0.0809
best: 0.0235 (ESA (Edge set attention, no positional encodings))
Graph Propagation Transformer for Graph Representation Learning arXiv:2305.11424