Node2Vec — how does it learn graph node embeddings?
mediumAnswer
- Random walks starting from each node → treat walks as 'sentences', apply Word2Vec skip-gram → embed nodes.
- Biased walks (p, q) control breadth (BFS-like) vs depth (DFS-like): controls whether embeddings capture structural equivalence or community proximity.
- Uses: link prediction, node classification, community detection preprocessing.
- Foundational shallow graph embedding; modern replacement: GNNs (GraphSAGE, GAT).
Check yourself — multiple choice
- Random
- Random walks → Word2Vec skip-gram on node sequences; biased walks (p, q) tune BFS (structural) vs DFS (community); superseded by GNNs (GraphSAGE, GAT)
- Same as PCA
- Not real
Node2Vec: biased random walks + Word2Vec skip-gram on nodes.
#representation-learning#applications
Practise Unsupervised Learning
214 interview questions in this topic.
Related questions
- Self-supervised graph learning — approaches.
- 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?