Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
This work addresses the challenge of leveraging unlabeled graph data for GNNs, offering a plug-in method to boost performance in applications like recommendation systems, though it is incremental as it builds on existing self-supervised and meta-learning ideas.
The paper tackles the problem of improving graph neural networks (GNNs) by proposing a self-supervised auxiliary learning framework that automatically balances auxiliary tasks to enhance generalization, resulting in consistent performance gains in node classification and link prediction.
In recent years, graph neural networks (GNNs) have been widely adopted in the representation learning of graph-structured data and provided state-of-the-art performance in various applications such as link prediction, node classification, and recommendation. Motivated by recent advances of self-supervision for representation learning in natural language processing and computer vision, self-supervised learning has been recently studied to leverage unlabeled graph-structured data. However, employing self-supervision tasks as auxiliary tasks to assist a primary task has been less explored in the literature on graphs. In this paper, we propose a novel self-supervised auxiliary learning framework to effectively learn graph neural networks. Moreover, this work is the first study showing that a meta-path prediction is beneficial as a self-supervised auxiliary task for heterogeneous graphs. Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance. The proposed method identifies an effective combination of auxiliary tasks and automatically balances them to improve the primary task. Our methods can be applied to any graph neural network in a plug-in manner without manual labeling or additional data. Also, it can be extended to any other auxiliary tasks. Our experiments demonstrate that the proposed method consistently improves the performance of node classification and link prediction.