Learning Convolutional Neural Networks for Graphs

17 May 2016Mathias NiepertMohamed AhmedKonstantin Kutzkov

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Graph Classification D&D PSCN Accuracy 76.27% # 27
Graph Classification IMDb-B PSCN Accuracy 71.00% # 21
Graph Classification MUTAG PATCHY-SAN Accuracy 92.63% # 5
Graph Classification MUTAG PSCN Accuracy 88.95% # 18
Graph Classification NCI1 PSCN Accuracy 76.34% # 26
Graph Classification PTC PATCHY-SAN Accuracy 60.00% # 27

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