An End-to-End Deep Learning Architecture for Graph Classification

AAAI-18 2018 Muhan ZhangZhicheng CuiMarion NeumannYixin Chen

Neural networks are typically designed to deal with data in tensor forms. In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Graph Classification COLLAB DGCNN (sum) Accuracy 69.45% # 22
Graph Classification COLLAB DGCNN Accuracy 73.76% # 19
Graph Classification D&D DGCNN Accuracy 79.37% # 14
Graph Classification D&D DGCNN (sum) Accuracy 78.72% # 17
Graph Classification IMDb-B DGCNN Accuracy 70.03% # 23
Graph Classification IMDb-B DGCNN (sum) Accuracy 51.69% # 27
Graph Classification IMDb-M DGCNN Accuracy 47.83% # 21
Graph Classification IMDb-M DGCNN (sum) Accuracy 42.76% # 25
Graph Classification MUTAG DGCNN Accuracy 85.83% # 38
Graph Classification NCI1 DGCNN (sum) Accuracy 69.00% # 37
Graph Classification NCI1 DGCNN Accuracy 74.44% # 29
Graph Classification PROTEINS DGCNN (sum) Accuracy 76.26% # 28
Graph Classification PROTEINS DGCNN Accuracy 75.54% # 32
Graph Classification PTC DGCNN Accuracy 58.59 # 29

Methods used in the Paper