Automated Graph Learning via Population Based Self-Tuning GCN

TL;DR

This paper introduces a self-tuning and population-based training method for GCNs to automate hyperparameter optimization, improving deep GCN training on benchmark datasets.

Contribution

It proposes a novel self-tuning GCN approach with an alternate training algorithm and extends it with population-based training for better hyperparameter optimization.

Findings

Enhanced deep GCN performance on benchmarks

Effective hyperparameter optimization with proposed methods

Outperforms several baseline approaches

Abstract

Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification. Traditional GCN models suffer from the issues of overfitting and oversmoothing, while some recent techniques like DropEdge could alleviate these issues and thus enable the development of deep GCN. However, training GCN models is non-trivial, as it is sensitive to the choice of hyperparameters such as dropout rate and learning weight decay, especially for deep GCN models. In this paper, we aim to automate the training of GCN models through hyperparameter optimization. To be specific, we propose a self-tuning GCN approach with an alternate training algorithm, and further extend our approach by incorporating the population based training scheme. Experimental results on three benchmark datasets demonstrate the effectiveness of our approaches on optimizing multi-layer GCN, compared with several representative baselines.