AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning
This addresses incomplete graph data issues for multimedia applications, but it is incremental as it builds on existing graph representation learning methods.
The paper tackles the problem of missing node attributes in attribute graphs, which negatively impacts media knowledge discovery, by proposing AmGCL, a framework that uses self-supervised contrastive learning and outperforms state-of-the-art methods in feature imputation and node classification tasks on multiple real-world datasets.
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.