AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning

TL;DR

AmGCL is a novel self-supervised contrastive learning framework designed to impute missing node attributes in attribute graphs, improving feature reconstruction and node classification performance in multimedia applications.

Contribution

The paper introduces AmGCL, combining Dirichlet energy minimization and contrastive learning to effectively handle missing attributes in graphs, surpassing existing methods.

Findings

Outperforms state-of-the-art in feature imputation

Achieves higher accuracy in node classification

Effective on multiple real-world datasets

Abstract

Attribute graphs are ubiquitous in multimedia applications, and graph representation learning (GRL) has been successful in analyzing attribute graph data. However, incomplete graph data and missing node attributes can have a negative impact on media knowledge discovery. Existing methods for handling attribute missing graph have limited assumptions or fail to capture complex attribute-graph dependencies. To address these challenges, we propose Attribute missing Graph Contrastive Learning (AmGCL), a framework for handling missing node attributes in attribute graph data. AmGCL leverages Dirichlet energy minimization-based feature precoding to encode in missing attributes and a self-supervised Graph Augmentation Contrastive Learning Structure (GACLS) to learn latent variables from the encoded-in data. Specifically, AmGCL utilizies feature reconstruction based on structure-attribute energy minimization while maximizes the lower bound of evidence for latent representation mutual information. Our experimental results on multiple real-world datasets demonstrate that AmGCL outperforms state-of-the-art methods in both feature imputation and node classification tasks, indicating the effectiveness of our proposed method in real-world attribute graph analysis tasks.