Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend... (read more)

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Node Classification Citeseer PPNP Accuracy 75.83% # 6
Validation YES # 1
Node Classification Citeseer APPNP Accuracy 75.73% # 7
Node Classification Cora APPNP Accuracy 85.09% # 12
Validation YES # 1
Node Classification Cora PPNP Accuracy 85.29% # 10
Validation YES # 1
Node Classification MS ACADEMIC APPNP Accuracy 93.27% # 1
Node Classification Pubmed APPNP Accuracy 79.73% # 21
Validation YES # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet