Graph Self Supervised Learning: the BT, the HSIC, and the VICReg
Self-supervised learning and pre-training strategies have developed over the last few years especially for Convolutional Neural Networks (CNNs). Recently application of such methods can also be noticed for Graph Neural Networks (GNNs) . In this paper, we have used a graph based self-supervised learning strategy with different loss functions (Barlow Twins[Zbontar et al., 2021], HSIC[Tsai et al., 2021], VICReg[Bardes et al., 2021]) which have shown promising results when applied with CNNs previously. We have also proposed a hybrid loss function combining the advantages of VICReg and HSIC and called it as VICRegHSIC. The performance of these aforementioned methods have been compared when applied to different datasets such as MUTAG, PROTEINS and IMDB-Binary. Moreover, the impact of different batch sizes, projector dimensions and data augmentation strategies have also been explored
READ FULL TEXT