Capsule Graph Neural Network

The high-quality node embeddings learned from the Graph Neural Networks (GNNs) have been applied to a wide range of node-based applications and some of them have achieved state-of-the-art (SOTA) performance. However, when applying node embeddings learned from GNNs to generate graph embeddings, the scalar node representation may not suffice to preserve the node/graph properties efficiently, resulting in sub-optimal graph embeddings... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Graph Classification COLLAB CapsGNN Accuracy 79.62% # 12
Graph Classification D&D CapsGNN Accuracy 75.38% # 31
Graph Classification ENZYMES CapsGNN Accuracy 54.67% # 21
Graph Classification IMDb-B CapsGNN Accuracy 73.10% # 15
Graph Classification IMDb-M CapsGNN Accuracy 50.27% # 14
Graph Classification MUTAG CapsGNN Accuracy 86.67% # 35
Graph Classification NCI1 CapsGNN Accuracy 78.35% # 24
Graph Classification PROTEINS CapsGNN Accuracy 76.28% # 28
Graph Classification RE-M12K CapsGNN Accuracy 46.62% # 5
Graph Classification RE-M5K CapsGNN Accuracy 52.88% # 4

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