> ML_ALGORITHM // NODE2VEC-RANDOM-WALK-EMBEDDINGS_v1.0
Node2Vec (Biased Random Walks)
Algorithmic framework for learning continuous feature representations for nodes in networks via biased random walks interpolating between BFS and DFS.
Graph Representation Learninggraph-relationalhigh-intrinsicmedium (1k-100k)
Back to All AlgorithmsComputational Complexity
Training Complexity:O(walks * length * |V| + skipgram_passes)
Inference Complexity:O(1) dictionary lookup
Hardware Profile
CPU Friendly:Yes
Requires GPU:No
Memory Footprint:low
Interpretability & Data
Interpretability Tier:high-intrinsic
Training Data Needs:medium (1k-100k)
Interpretability Assessment
Parameters p (return) and q (in-out) provide continuous interpolation between micro-network community and macro-structural role similarity.
Suitable Tasks & Supported Modalities
Suitable Tasks:
link predictionnode classificationgraph clustering
Supported Modalities:
graph
Implementing Libraries
Foundational Literature
Common Pitfalls & Warnings
- Purely transductive: cannot compute embeddings for new nodes added after training without re-running random walks