Hyper-SAGNN-E

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

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

Graphs5 results

Link PredictiononWordNet
AUC· 2019-11-06
0.89
SOTA
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs arXiv:1911.02613
Link PredictiononGPS
AUC· 2019-11-06
0.9520000000000001
SOTA
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs arXiv:1911.02613
Link PredictiononGPS
AUPR· 2019-11-06
0.7979999999999999
SOTA
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs arXiv:1911.02613
Link PredictiononWordNet
AUPR· 2019-11-06
0.705
best: 0.706 (Hyper-SAGNN-W)
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs arXiv:1911.02613
Link PredictiononMovieLens 1M
AUPR· 2019-11-06
0.7929999999999999
best: 0.81 (Hyper-SAGNN-W)
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs arXiv:1911.02613