Self-supervised graph learning — approaches.
hardAnswer
- (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
- Node2Vec — how does it learn graph node embeddings?
- Self-supervised audio — wav2vec 2 and HuBERT.
- How are multimodal embeddings unified across text / image / audio?
- Fine-tuning vs linear probe vs prompt-tuning — when do you use each?
- What is a 'foundation model' in the unsupervised sense?
- What is self-supervised learning and why does it matter?