DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

21 Apr 2019Rami Al-RfouDustin ZelleBryan Perozzi

Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\ feature engineering or labeled graphs)... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Graph Classification D&D DDGK Accuracy 83.14% # 2
Graph Classification MUTAG DDGK Accuracy 91.58% # 6
Graph Classification NCI1 DDGK Accuracy 68.10% # 38
Graph Classification PTC DDGK Accuracy 63.14% # 19

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