Optimization of Graph Neural Networks with Natural Gradient Descent

In this work, we propose to employ information-geometric tools to optimize a graph neural network architecture such as the graph convolutional networks. More specifically, we develop optimization algorithms for the graph-based semi-supervised learning by employing the natural gradient information in the optimization process... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification Citeseer SSP Accuracy 80.52% # 1
Node Classification CiteSeer with Public Split: fixed 20 nodes per class SSP Accuracy 74.28% # 6
Node Classification Cora SSP Accuracy 90.16% # 1
Node Classification Cora with Public Split: fixed 20 nodes per class SSP Accuracy 82.84% # 17
Node Classification Pubmed SSP Accuracy 89.36% # 2
Node Classification PubMed with Public Split: fixed 20 nodes per class SSP Accuracy 80.06% # 11

Methods used in the Paper