by eliorc

eliorc /node2vec

Implementation of the node2vec algorithm.

547 Stars 148 Forks Last release: 4 months ago (v0.3.2) MIT License 35 Commits 1 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:



Python3 implementation of the node2vec algorithm Aditya Grover, Jure Leskovec and Vid Kocijan. node2vec: Scalable Feature Learning for Networks. A. Grover, J. Leskovec. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2016.


pip install node2vec


import networkx as nx
from node2vec import Node2Vec

Create a graph

graph = nx.fast_gnp_random_graph(n=100, p=0.5)

Precompute probabilities and generate walks - ON WINDOWS ONLY WORKS WITH workers=1

node2vec = Node2Vec(graph, dimensions=64, walk_length=30, num_walks=200, workers=4) # Use temp_folder for big graphs

Embed nodes

model =, min_count=1, batch_words=4) # Any keywords acceptable by gensim.Word2Vec can be passed, diemnsions and workers are automatically passed (from the Node2Vec constructor)

Look for most similar nodes

model.wv.most_similar('2') # Output node names are always strings

Save embeddings for later use


Save model for later use

Embed edges using Hadamard method

from node2vec.edges import HadamardEmbedder

edges_embs = HadamardEmbedder(keyed_vectors=model.wv)

Look for embeddings on the fly - here we pass normal tuples

edges_embs[('1', '2')] ''' OUTPUT array([ 5.75068220e-03, -1.10937878e-02, 3.76693785e-01, 2.69105062e-02, ... ... .... ..................................................................], dtype=float32) '''

Get all edges in a separate KeyedVectors instance - use with caution could be huge for big networks

edges_kv = edges_embs.as_keyed_vectors()

Look for most similar edges - this time tuples must be sorted and as str

edges_kv.most_similar(str(('1', '2')))

Save embeddings for later use




  • Node2Vec
    1. graph
      : The first positional argument has to be a networkx graph. Node names must be all integers or all strings. On the output model they will always be strings.
    2. dimensions
      : Embedding dimensions (default: 128)
    3. walk_length
      : Number of nodes in each walk (default: 80)
    4. num_walks
      : Number of walks per node (default: 10)
    5. p
      : Return hyper parameter (default: 1)
    6. q
      : Inout parameter (default: 1)
    7. weight_key
      : On weighted graphs, this is the key for the weight attribute (default: 'weight')
    8. workers
      : Number of workers for parallel execution (default: 1)
    9. sampling_strategy
      : Node specific sampling strategies, supports setting node specific 'q', 'p', 'numwalks' and 'walklength'. Use these keys exactly. If not set, will use the global ones which were passed on the object initialization`
    10. quiet
      : Boolean controlling the verbosity. (default: False)
    11. temp_folder
      : String path pointing to folder to save a shared memory copy of the graph - Supply when working on graphs that are too big to fit in memory during algorithm execution.
    method: Accepts any key word argument acceptable by gensim.Word2Vec


is an abstract class which all the concrete edge embeddings class inherit from. The classes are
which their practical definition could be found in the paper on table 1 Notice that edge embeddings are defined for any pair of nodes, connected or not and even node with itself.
  • Constructor:

    1. keyed_vectors
      : A gensim.models.KeyedVectors instance containing the node embeddings
    2. quiet
      : Boolean controlling the verbosity. (default: False)
  • EdgeEmbedder.__getitem__(item)
    method, better known as
    1. item
      - A tuple consisting of 2 nodes from the
      passed in the constructor. Will return the embedding of the edge.
  • EdgeEmbedder.as_keyed_vectors
    method: Returns a
    instance with all possible node pairs in a sorted manner as string. For example, for nodes ['1', '2', '3'] we will have as keys "('1', '1')", "('1', '2')", "('1', '3')", "('2', '2')", "('2', '3')" and "('3', '3')".


  • Node names in the input graph must be all strings, or all ints
  • Parallel execution not working on Windows (
    known issue). To run non-parallel on Windows pass
    on the
    's constructor


  • [x] Parallel implementation for walk generation
  • [ ] Parallel implementation for probability precomputation

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.