Skip to main content

Table 2 Graph classification datasets summary and results

From: Quantum walk neural networks with feature dependent coins

  Enzymes Mutag NCI1
Graphs 600 188 4110
Average Nodes 33 18 30
Max Nodes 126 28 111
Max Degree 9 4 4
Node Classes 3 7 37
Graph Classes 6 2 2
  Classification Accuracy ± STD
GCN 0.31±0.06 0.87±0.10 0.69±0.02
DCNN 0.27±0.08 0.89±0.10 0.69±0.01
GAT 0.32±0.04 0.89±0.06 0.66±0.03
QWNN (cen) 0.26±0.03 0.90±0.09 0.76±0.01
QWNN (inv) 0.33±0.04 0.88±0.04 0.73±0.02
WL 0.59±0.01 0.84±0.01 0.85±0.00
SP 0.41±0.02 0.87±0.01 0.73±0.00
  1. The best performing neural networks and the overal best performing methods are bolded for each task