2022/07/05 by Adnan Ali, Ali, Adnan, Jinlong Li +1 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #I.2 #Machine Learning (cs.LG) #Recommender Systems and Techniques
paper · pdf · doi:10.48550/arxiv.2207.01792
openalex publication_date 2022/07/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Self-Supervised learning aims to eliminate the need for expensive annotation in graph representation learning, where graph contrastive learning (GCL) is trained with the self-supervision signals containing data-data pairs. These data-data pairs are generated with augmentation employing stochastic functions on the original graph. We argue that some features can be more critical than others depending on the downstream task, and applying stochastic function uniformly, will vandalize the influential features, leading to diminished accuracy. To fix this issue, we introduce a Feature Based Adaptive Augmentation (FebAA) approach, which identifies and preserves potentially influential features and corrupts the remaining ones. We implement FebAA as plug and play layer and use it with state-of-the-art Deep Graph Contrastive Learning (GRACE) and Bootstrapped Graph Latents (BGRL). We successfully improved the accuracy of GRACE and BGRL on eight graph representation learning's benchmark datasets.