2023/03/24 by Yifu Chen, Chen, Yifu, Qianqian Ren +3
Computer Science · Health Professions · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Health Literacy and Information Accessibility #Machine Learning (cs.LG) #Recommender Systems and Techniques
paper · pdf · doi:10.48550/arxiv.2303.15182
openalex publication_date 2023/03/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Graph augmentations are essential for graph contrastive learning. Most existing works use pre-defined random augmentations, which are usually unable to adapt to different input graphs and fail to consider the impact of different nodes and edges on graph semantics. To address this issue, we propose a framework called Hybrid Augmented Automated Graph Contrastive Learning (HAGCL). HAGCL consists of a feature-level learnable view generator and an edge-level learnable view generator. The view generators are end-to-end differentiable to learn the probability distribution of views conditioned on the input graph. It insures to learn the most semantically meaningful structure in terms of features and topology, respectively. Furthermore, we propose an improved joint training strategy, which can achieve better results than previous works without resorting to any weak label information in the downstream tasks and extensive evaluation of additional work.