How to use for graph classification

[PeterDeSOM]

So far, all that I've found the method for Graph Clustering is actually for node clustering or not a fully unsupervised learning method. It means that they eventually need their label to train at the downstream task.

For example, it is;

• pretraining some datasets with the unlabeled using the contrastive learning method or others. (No output channel or number of classes to be clustered is required)
• then finetuning the dataset with its labels using the supervised learning method.

I'm finding a fully unsupervised learning method for Graph-Level Clustering/Classification. Or, I'd like to know how to employ your model in a fully unsupervised learning method to classify lots of graph data that cannot be labeled by human efforts.

Question. Could you show me a little direction to use the embedding from your model for the Graph-Level Classification/Clustering without its labels such as KMeans at the downstream task?

[THINK2TRY]

Hi, @PeterDeSOM Thanks for your attention to our work! Actually, GraphMAE is an unsupervised representation learning method, which pre-trains GNNs and learns node-level and graph-level embeddings without relying on any labeled data. The embeddings can be directly applied to any downstream task like clustering without finetuning.

In our experimental setting, we simply train a linear classifier rather than finetune the GNN to evaluate the quality of the learned embeddings. Graph clustering such as KMeans can also be used for evaluation.