EasyDeepLearn

Node2Vec — how does it learn graph node embeddings?

medium

Answer

  • 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  • Random walks → Word2Vec skip-gram on node sequences; biased walks (p, q) tune BFS (structural) vs DFS (community); superseded by GNNs (GraphSAGE, GAT)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