DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model

10 Dec 2017 Bo Wu Yang Liu Bo Lang Lei Huang

Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Graph Classification AIDS DGCNN Accuracy 65.1 # 1
Graph Classification COLLAB DGCNN Accuracy 68.34% # 25
Graph Classification D&D DGCNN Accuracy 77.21% # 25
Graph Classification PROTEINS DGCNN Accuracy 75.1% # 41
Graph Classification PTC DGCNN Accuracy 65.43% # 16

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions