Archives for contrastive self-supervised learning
The Graph Contrastive Learning aims to learn the graph representation with the help of contrastive learning.
On the contrary, to collapse in contrastive methods, FAIR identified non-contrastive methods to suffer from a lesser collapse problem of a different nature.
By merging self-supervised learning and contrastive learning we can make it contrastive self-supervised learning, which is also a part of self-supervised learning.