Towards Deeper Graph Neural Networks

18 Jul 2020Meng LiuHongyang GaoShuiwang Ji

Graph neural networks have shown significant success in the field of graph representation learning. Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification AMZ Computers DAGNN (Ours) Accuracy 84.5 # 1
Node Classification AMZ Photo DAGNN (Ours) Accuracy 92% # 2
Node Classification CiteSeer with Public Split: fixed 20 nodes per class DAGNN (Ours) Accuracy 73.3% # 8
Node Classification Coauthor CS DAGNN (Ours) Accuracy 92.8% # 3
Node Classification Coauthor Physics DAGNN (Ours) Accuracy 94 # 1
Node Classification Cora with Public Split: fixed 20 nodes per class DAGNN (Ours) Accuracy 84.4% # 4
Node Classification PubMed with Public Split: fixed 20 nodes per class DAGNN (Ours) Accuracy 80.5% # 5

Methods used in the Paper