EasyDeepLearn

Self-supervised graph learning — approaches.

hard

Answer

  • (1) Node-level: contrastive on augmented views (drop edges/nodes/features), GraphCL.
  • (2) Predict masked node attributes (MaskGAE).
  • (3) Motif / structure prediction.
  • (4) Bootstrap approaches (BGRL, analog of BYOL for graphs).
  • Used to pretrain GNNs on unlabeled graphs before fine-tuning on labels.
  • Standard in drug discovery / molecular property pipelines (huge unlabeled compound libraries).
Check yourself — multiple choice
  • Random
  • Contrastive with edge/node/feature dropping (GraphCL) / mask reconstruction (MaskGAE) / bootstrap BGRL / motif prediction — pretrain GNNs on unlabeled graphs
  • Same as classifier
  • Not real

Graph SSL: GraphCL / MaskGAE / BGRL; pretrain GNNs on unlabeled graphs.

#representation-learning#applications

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions