FDGATII

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Graphs4 results

Node ClassificationonWisconsin
Accuracy· 2021-10-21
86.2745
best: 88.77 (MGNN + Hetero-S (6 layers))
SOTA
FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping arXiv:2110.11464
Node ClassificationonTexas
Accuracy· 2021-10-21
80.5405
best: 93.09 (MGNN + Hetero-S (8 layers))
SOTA
FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping arXiv:2110.11464
Node ClassificationonCornell
Accuracy· 2021-10-21
82.4324
SOTA
FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping arXiv:2110.11464
Node ClassificationonChameleon
Accuracy· 2021-10-21
65.1754
best: 70.18 (JKNet + Hetero-S (8 layers))
SOTA
FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping arXiv:2110.11464