ANGPN jointly learns an adaptive neighborhood graph and propagates node features through it, improving semi-supervised classification accuracy by a few points over fixed-graph GCN on SVHN, CIFAR, 20News, and CoraML.
Clustering and projected clustering with adaptive neighbors,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network
ANGPN jointly learns an adaptive neighborhood graph and propagates node features through it, improving semi-supervised classification accuracy by a few points over fixed-graph GCN on SVHN, CIFAR, 20News, and CoraML.