Contrastive learning and generative methodologies in graph self-supervised learning offer efficient strategies for managing graph data with scarce labels. Among these techniques, the masked graph ...

Researchers introduced X-CLR, a novel contrastive learning method using graph-based sample relationships. This approach ...

By leveraging graph message-passing layers, graph feature augmentation and contrastive learning, the proposed CGAE embeds highly discriminative latent embeddings by reconstructing graph features w.r.t ...

Abstract: Contrastive learning and generative methodologies in graph self-supervised learning offer efficient strategies for managing graph data with scarce labels. Among these techniques, the masked ...

Researchers introduced X-CLR, a novel contrastive learning method using graph-based sample relationships. This approach outperformed traditional models like SimCLR in low-data regimes, enhancing ...