Hyperbolic Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space, which has been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbolic geometry offers an exciting alternative, as it enables embeddings with much smaller distortion... (read more)

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification Cora HGCN Accuracy 79.9% # 46
Link Prediction PPI HGCN Accuracy 84.5 # 1
Node Classification Pubmed HGCN Accuracy 80.3% # 16

Methods used in the Paper


METHOD TYPE
GCN
Graph Models