Optimization of Graph Neural Networks with Natural Gradient Descent
This work addresses optimization challenges in graph-based semi-supervised learning, offering a novel approach that could improve efficiency and accuracy in domains like social network analysis or bioinformatics.
The authors tackled the optimization of graph neural networks by using natural gradient descent, resulting in superior performance over existing algorithms like ADAM and SGD as demonstrated through extensive numerical studies.
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. This allows us to efficiently exploit the geometry of the underlying statistical model or parameter space for optimization and inference. To the best of our knowledge, this is the first work that has utilized the natural gradient for the optimization of graph neural networks that can be extended to other semi-supervised problems. Efficient computations algorithms are developed and extensive numerical studies are conducted to demonstrate the superior performance of our algorithms over existing algorithms such as ADAM and SGD.