Automated Graph Learning via Population Based Self-Tuning GCN
This work addresses the challenge of training GCN models, which are sensitive to hyperparameters, for researchers and practitioners in graph learning, but it is incremental as it builds on existing hyperparameter optimization techniques.
The paper tackles the problem of automating hyperparameter optimization for Graph Convolutional Networks (GCNs) to address issues like overfitting and oversmoothing, proposing a self-tuning GCN with population-based training that shows effectiveness on three benchmark datasets compared to baselines.
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.