AI Paper Atlas

Research map / Graph learning / GNN architectures

SelfSAGCN: Self-Supervised Semantic Alignment for Graph Convolution Network

Xu Yang, Cheng Deng, Zhiyuan Dang, Kun Wei, Junchi Yan

CVPR 2021 · Graph learning › GNN architectures · approach: Graph structure learning

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Cora, 1 label per classaccuracy: 60.2(0.9) -> 63.5(0.8)Improved
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Citeseer, 1 label per classaccuracy: 52.2(1.3) -> 57.5(3.7)Improved
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Pubmed, 1 label per classaccuracy: 60.3(6.1) -> 65.0(3.3)Improved
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Cora, 2 labels per classaccuracy: 68.3(0.9) -> 71.7(0.6)Improved
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Citeseer, 2 labels per classaccuracy: 60.1(1.3) -> 68.3(1.2)Improved
Use SelfSAGCN instead of DAGNNsemi-supervised node classification · Pubmed, 2 labels per classaccuracy: 65.3(2.7) -> 70.9(1.9)Improved
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Cora, 5 labels per classaccuracy: 73.0(1.2) -> 75.1(0.7)Improved
Use SelfSAGCN instead of Shoestringsemi-supervised node classification · Citeseer, 5 labels per classaccuracy: 64.2(1.5) -> 71.9(1.3)Improved
Use SelfSAGCN instead of SGCsemi-supervised node classification · Pubmed, 5 labels per classaccuracy: 71.4(2.9) -> 73.0(2.1)Improved
Use SelfSAGCN instead of DAGNNimage graph classification · STL-10, 1 label per classaccuracy: 87.5(0.5) -> 92.1(0.2)Improved
Use SelfSAGCN instead of DAGNNimage graph classification · CIFAR-10, 1 label per classaccuracy: 61.2(0.8) -> 65.8(0.7)Improved
Use SelfSAGCN instead of DAGNNimage graph classification · STL-10, 2 labels per classaccuracy: 89.0(0.9) -> 94.3(0.3)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy