GraphSAGE (Hamilton et al., [2017a])

Reported on 6 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.

Graphs6 results

Node ClassificationonFlickr
Accuracy· 2017-06-07
0.641
best: 0.682 (GCN+GAugM (Zhao et al., 2021))
SOTA
Inductive Representation Learning on Large Graphs arXiv:1706.02216
Node ClassificationonFacebook
Accuracy· 2017-06-07
38.9
best: 91.9 (DEMO-Net(weight))
Inductive Representation Learning on Large Graphs arXiv:1706.02216
Node ClassificationonBrazil Air-Traffic
Accuracy· 2017-06-07
0.404
best: 0.516 (GCN_cheby (Kipf and Welling, 2017))
Inductive Representation Learning on Large Graphs arXiv:1706.02216
Node ClassificationonWiki-Vote
Accuracy· 2017-06-07
24.5
best: 99.8 (DEMO-Net(weight))
Inductive Representation Learning on Large Graphs arXiv:1706.02216
Node ClassificationonEurope Air-Traffic
Accuracy· 2017-06-07
27.2
best: 46 (GCN_cheby (Kipf and Welling, 2017))
Inductive Representation Learning on Large Graphs arXiv:1706.02216
Node ClassificationonUSA Air-Traffic
Accuracy· 2017-06-07
31.6
best: 64.7 (DEMO-Net(weight))
Inductive Representation Learning on Large Graphs arXiv:1706.02216