Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2025

Abstract

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability. Typically, GAEs take incomplete graphs as input and predict missing elements, such as masked node features or edges. Although effective, our experimental investigation reveals that traditional feature or edge masking paradigms primarily capture low-frequency signals in the graph and fail to learn expressive structural information. To address these issues, we propose Graph Positional Autoencoders (GraphPAE), which employ a dual-path architecture to reconstruct both node features and positions. Specifically, the feature path uses positional encoding to enhance the message-passing processing, improving the GAEs' ability to predict the corrupted information. The position path, on the other hand, leverages node representations to refine positions and approximate eigenvectors, thereby enabling the encoder to learn diverse frequency information. We conduct extensive experiments to verify the effectiveness of GraphPAE, including heterophilic node classification, graph property prediction, and transfer learning. The results demonstrate that GraphPAE achieves state-of-the-art performance and consistently outperforms the baselines by a large margin.

Keywords

Graph Neural Networks, Self-supervised Learning, Graph Autoen-coders, Positional Encoding

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

KDD '25: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Toronto, Canada, August 3-7

Volume

2

First Page

1867

Last Page

1878

Identifier

10.1145/3711896.3736990

Publisher

ACM

City or Country

New York

Download

Share

COinS