Instance Discrimination for Link Prediction
For graph link prediction tasks, this work provides new self-supervised models that match supervised performance, particularly benefiting unattributed graphs.
The paper adapts instance discrimination models to link prediction, showing that performance depends on augmentation. It introduces L-GRACE and L-BGRL models based on link representations, achieving state-of-the-art results on unattributed graphs.
Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification. However, fewer contributions have tackled the link prediction task. In this contribution, we propose to adapt existing methods to this context. We first provide a rigorous evaluation of existing self-supervised models in the field of link prediction, showing that the main performance depends on the augmentation process (like in computer vision). We then propose a new structural augmentation based on the community structure that is relevant for link prediction. Our main contribution introduces two new models, L-GRACE and L-BGRL, based on link representations instead of node representations, which improve the performance of the existing methods, especially on unattributed graphs, and we show that they perform on par with the state of the art, both in supervised and self-supervised contexts.