Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction

TL;DR

This paper introduces deepened graph auto-encoders that incorporate standard auto-encoders and residual connections to improve the stability and performance of link prediction in graph neural networks.

Contribution

It proposes novel deep GAE architectures that integrate standard auto-encoders and residual connections, enabling stable, deep models for link prediction.

Findings

Deepened GAEs outperform shallow models on benchmark datasets.

Theoretical proof of expressive power via polynomial filters.

Models achieve competitive results in link prediction tasks.

Abstract

Graph neural networks have been used for a variety of learning tasks, such as link prediction, node classification, and node clustering. Among them, link prediction is a relatively under-studied graph learning task, with current state-of-the-art models based on one- or two-layer of shallow graph auto-encoder (GAE) architectures. In this paper, we focus on addressing a limitation of current methods for link prediction, which can only use shallow GAEs and variational GAEs, and creating effective methods to deepen (variational) GAE architectures to achieve stable and competitive performance. Our proposed methods innovatively incorporate standard auto-encoders (AEs) into the architectures of GAEs, where standard AEs are leveraged to learn essential, low-dimensional representations via seamlessly integrating the adjacency information and node features, while GAEs further build multi-scaled low-dimensional representations via residual connections to learn a compact overall embedding for link prediction. Empirically, extensive experiments on various benchmarking datasets verify the effectiveness of our methods and demonstrate the competitive performance of our deepened graph models for link prediction. Theoretically, we prove that our deep extensions inclusively express multiple polynomial filters with different orders.