DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification

5 Jun 2019 Jun Wu Jingrui He Jiejun Xu

Graph data widely exist in many high-impact applications. Inspired by the success of deep learning in grid-structured data, graph neural network models have been proposed to learn powerful node-level or graph-level representation... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification BlogCatalog DEMO-Net(weight) Accuracy 84.9% # 1
Node Classification Brazil Air-Traffic DEMO-Net(weight) Accuracy 0.543 # 1
Graph Classification ENZYMES DEMO-Net(weight) Accuracy 27.2 # 30
Node Classification Europe Air-Traffic DEMO-Net(weight) Accuracy 45.9 # 2
Node Classification Facebook DEMO-Net(weight) Accuracy 91.9 # 1
Node Classification Flickr DEMO-Net(weight) Accuracy 0.656 # 1
Graph Classification MUTAG DEMO-Net(weight) Accuracy 81.4% # 52
Graph Classification PROTEINS DEMO-Net(weight) Accuracy 70.8% # 67
Graph Classification PTC DEMO-Net(weight) Accuracy 57.2% # 31
Node Classification USA Air-Traffic DEMO-Net(weight) Accuracy 64.7 # 1
Node Classification Wiki-Vote DEMO-Net(weight) Accuracy 99.8 # 1

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions