Task 2: Self-supervised training of 2nd stage

[Ishaan Kumar]

1. We want to evaluate the effects of training the 2nd stage in a completely self-supervised setting.
2. Two self-supervised tasks are mentioned in the paper: graph edit distance and graph structure similarity .
3. The goal is to implement or reuse existing implementation of both of them. Rest of the pipeline remains same and changes possibly include model changes, dataloader changes (not necessary).

[Philippe Lelièvre]

Results :

unsupervised_pretrain_graph_level_from_scratch
58.36488029188599

unsupervised_pretrain_graph_without_graph_level_pretraining
63.143007055658515

unsupervised_pretrain_graph_contextpred_weight
56.02703642285913

unsupervised_pretrain_graph_with_masking_weights
67.88642939178769

unsupervised_pretrain_graph_info_graph
70.1961267598414