Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)


Version License repo size Arxiv build badge coverage badge

Karate Club is an unsupervised machine learning extension library for NetworkX.

Please look at the Documentation, relevant Paper, Promo Video, and External Resources.

Karate Club consists of state-of-the-art methods to do unsupervised learning on graph structured data. To put it simply it is a Swiss Army knife for small-scale graph mining research. First, it provides network embedding techniques at the node and graph level. Second, it includes a variety of overlapping and non-overlapping community detection methods. Implemented methods cover a wide range of network science (NetSci, Complenet), data mining (ICDM, CIKM, KDD), artificial intelligence (AAAI, IJCAI) and machine learning (NeurIPS, ICML, ICLR) conferences, workshops, and pieces from prominent journals.

The newly introduced graph classification datasets are available at SNAP, TUD Graph Kernel Datasets, and GraphLearning.io.


If you find Karate Club and the new datasets useful in your research, please consider citing the following paper:

       title = {{Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs}},
       author = {Benedek Rozemberczki and Oliver Kiss and Rik Sarkar},
       year = {2020},
       pages = {3125–3132},
       booktitle = {Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM '20)},
       organization = {ACM},

A simple example

Karate Club makes the use of modern community detection techniques quite easy (see here for the accompanying tutorial). For example, this is all it takes to use on a Watts-Strogatz graph Ego-splitting:

import networkx as nx
from karateclub import EgoNetSplitter

g = nx.newman_watts_strogatz_graph(1000, 20, 0.05)

splitter = EgoNetSplitter(1.0)



Models included

In detail, the following community detection and embedding methods were implemented.

Overlapping Community Detection

Non-Overlapping Community Detection

Neighbourhood-Based Node Level Embedding

Structural Node Level Embedding

Attributed Node Level Embedding

Meta Node Embedding

Graph Level Embedding

Head over to our documentation to find out more about installation and data handling, a full list of implemented methods, and datasets. For a quick start, check out our examples.

If you notice anything unexpected, please open an issue and let us know. If you are missing a specific method, feel free to open a feature request. We are motivated to constantly make Karate Club even better.


Karate Club can be installed with the following pip command.

$ pip install karateclub

As we create new releases frequently, upgrading the package casually might be beneficial.

$ pip install karateclub --upgrade

Running examples

As part of the documentation we provide a number of use cases to show how the clusterings and embeddings can be utilized for downstream learning. These can accessed here with detailed explanations.

Besides the case studies we provide synthetic examples for each model. These can be tried out by running the example scripts. In order to run one of the examples, the Graph2Vec snippet:

$ cd examples/whole_graph_embedding/
$ python graph2vec_example.py

Running tests

$ python setup.py test


  • GL2vec : RuntimeError: you must first build vocabulary before training the model

    GL2vec : RuntimeError: you must first build vocabulary before training the model

    Hello, First thanks for your work, it's just great.

    However, I have an error while trying to run GL2vec on my dataset, while it works perfectly with the example. Where is exactly this type of error coming from ?

    Thanks in advance

    opened by hug0prevoteau 14
  • How to build my own dataset?

    How to build my own dataset?

    I have to build graphs, and following that I have to generate graph embedding.

    I checked the documentation i.e. https://karateclub.readthedocs.io/.

    But I didn't understand how to build my own graphs.

    1. Can you please point out a sample code where you create dataset from scratch?
    2. I have already checked code here. But they all load pre-defined dataset.
    3. Can you show any code snippet where you create graph i.e. create nodes and add edges.
    4. How to set attributes (features) for the nodes and edges?

    Thanks in advance for your help.

    I am following the https://karateclub.readthedocs.io/en/latest/notes/installation.html.

    opened by smith-co 9
  • About GL2vec

    About GL2vec

    Hello, thanks for the awesome work!!

    It seems that there are 2 mistakes in the implementation of GL2vec module.

    The first one is :

    in the code below, """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" def _create_line_graph(self, graph): r"""Getting the embedding of graphs. Arg types: * graph (NetworkX graph) - The graph transformed to be a line graph. Return types: * line_graph (NetworkX graph) - The line graph of the source graph. """ graph = nx.line_graph(graph) node_mapper = {node: i for i, node in enumerate(graph.nodes())} edges = [[node_mapper[edge[0]], node_mapper[edge[1]]] for edge in graph.edges()] line_graph = nx.from_edgelist(edges) return line_graph """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" when converting graph G to line graph LG, the method "_create_line_graph()" ignores the edge attribute of G. (It means that there will be no node arrtibutes in LG) so consequently, the method "WeisfeilerLehmanHashing" will not use the attribute information, and will always use the structural information (degree) instead.

    The second one is :

    The GL2vec module only returns the embedding of line graph. But in the original paper of GL2vec, they concatenate the embedding of graph and of line graph.
    Then named the framework "GL2vec", which means "Graph and Line graph to vector".

    Only use the embedding of line graph for downstream task may lead to worse performance.

    We noticed that when applying the embeddings to the graph classification task, (when graph both have node attribute and edge attribute) the performance (accuracy) are as follow: concat(G , LG) > G > LG

    Hope it helps :)

    opened by cheezy88 8
  • Classifying with graph2vec model

    Classifying with graph2vec model

    I'm able to obtain an embedding for a list of NetworkX graphs using graph2vec, and I was wondering if karateclub has a function to make classifications for graphs outside the training set? That is, given my embedding, I want to input a graph outside my original graph list (used in the model) and obtain a list of most similar graphs (something like a "most similar" function).

    opened by joseluisfalla 6
  • How to improve the performance of Graph2Vec model fit function ?

    How to improve the performance of Graph2Vec model fit function ?

    I tried to increase the performance of the Graph2Vec model by using increasing the worker parameter when initializing the model. But it seems that still, the model takes only 1 core to process the fit function.

    Is method I have used to assign the workers correct ? Is there another method to improve the performance ?

    model =  Graph2Vec(workers=28)
    graph_x = model.get_embedding()
    opened by 1209973 6
  • Is consecutive numeric indexing necessary for Graph2Vec?

    Is consecutive numeric indexing necessary for Graph2Vec?

    Thanks for the awesome work, networkx is truly helpful when we are dealing with Graph data structure.

    I'm trying to get graph embedding using Graph2vec so that we could compare similarity among graphs. But I'm stuck in this assertion: assert numeric_indices == node_indices, "The node indexing is wrong."

    Say if we have two graphs, each node in the graph represents a word. We build a mapping so that we could replace text with number. For example, whenever the word "Library" occurs in any graph, we label it with the number "2". In this case, the indexes inside one graph might not be consecutive because the mapping is created from a number of graphs.

    So is it still necessary for enforce consecutive indexing in this case? Or I understand the usage of Graph2Vec wrong?

    opened by bdeng3 5
  • Graph Embeddings using node features and inductivity

    Graph Embeddings using node features and inductivity


    First of all thank you for this amazing library! I have a serie of small graphs where each node contains features and I am trying to learn graph-level embedding in an unsupervised manner. However, I couldn't find how to load node features in the graphs before feeding them to a graph embedding algorithm. Could you describe the input needed by the algorithms ?

    Also, is it possible to generate embedding with some sort of forward function once the models are trained (without retraining the model) ? I.e. does the library support inductivity ?

    Thank you!

    opened by TrovatelliT 5
  • graph2vec implementation and graphs with missing nodes

    graph2vec implementation and graphs with missing nodes

    Hi there,

    first of all, thanks a lot for developing this, it has potential to simplify in-silico experiments on biological networks and I am grateful for that!

    I have a question related to the graph2vec implementation. The requirement of the package for graph notation is that nodes have to be named with integers starting from 0 and have to be consecutive. I am working with a collection of 9.000 small networks and would like to embed all of them into an N-dimensional space. Now, all those networks consist of about 25.000 nodes but in some networks these nodes (here it's really genes) are missing (not all genes are supposed to be present in all networks).

    If I rename all my nodes from actual gene names to integers and know that some networks don't have all the genes, I will end up with some networks without consecutive node names, e.g. there will be (..), 20, 21, 24, 25, (...) in one network and perhaps (...), 20, 21, 22, 24, 25, (...) in another. That would violate the requirement of being consecutive.

    My question is: is the implementation aware that a node 25 is the same object between the different networks? Or is it not important and in reality the embedding only takes into account the structure only and I should 'rename' all my networks separately to keep the node naming consecutive?

    opened by kajocina 5
  • Multithreading for WL hasing function

    Multithreading for WL hasing function


    Maybe just another suggestion. In the embedding algorithms, the WeisfeilerLehmanHashing function in the fit function could be time-consuming and the WL hashing function for each graph is independent. Therefore, maybe using multhreading from python can speed them up and I modify the code for my application of graph2vec:


    def fit(self, graphs):
        Fitting a Graph2Vec model.
        Arg types:
            * **graphs** *(List of NetworkX graphs)* - The graphs to be embedded.
        pool = ThreadPool(8)
        args_generator = [(graph, self.wl_iterations, self.attributed) for graph in graphs]
        documents = pool.starmap(WeisfeilerLehmanHashing, args_generator)
        #documents = [WeisfeilerLehmanHashing(graph, self.wl_iterations, self.attributed) for graph in graphs]
        documents = [TaggedDocument(words=doc.get_graph_features(), tags=[str(i)]) for i, doc in enumerate(documents)]
        model = Doc2Vec(documents,
        self._embedding = [model.docvecs[str(i)] for i, _ in enumerate(documents)]
    opened by zslwyuan 5
  • Update requirements

    Update requirements

    As it stands, setup.py has the following requirements which specify maximum versions:

    install_requires = [

    Is there a reason for the maximum versions, such as expired deprecated features used by karateclub? In my personal research, and in using the included test suite via python3 ./setup.py test, I have not encountered issues in upgrading the packages.

    $ pip3 install --upgrade --user networkx numpy pandas decorator
    $ pip3 list | grep "networkx\|numpy\|decorator\|pandas"
    decorator              5.1.1
    networkx               2.8.8
    numpy                  1.23.5
    pandas                 1.5.2

    Running the tests with these updated package yields the following:

    $ cd karateclub/
    $ pytest
    47 passed, 2540 warnings in 210.58s (0:03:30) 

    Yes, there are lots of warnings. Many are DeprecationWarnings. The current requirements generate 855 warnings.

    $ cd karateclub/
    $ pip3 install --user .
    $ pytest
    47 passed, 855 warnings in 225.49s (0:03:45)

    I suppose the question is: even with additional instances of DeprecationWarning, can we bump up the maximum requirements for this package? Or would the community feel better addressing the deprecation issues before continuing?

    For context, my motivation is to keep this package current; I'm currently held back (not actually, but per the setup requirements) by this package's maximum requirements. Does anyone have any thoughts?

    opened by WhatTheFuzz 4
  •     assert connected or self.allow_disjoint,

    assert connected or self.allow_disjoint, "Graph is not connected." AttributeError: 'Graph2Vec' object has no attribute 'allow_disjoint'

    I am receiving this error after running the provided example on my own dataset: a set of sub-graphs, each representing one sessions of my experiment. How may solve this?

    The graph is un-directed and without features.

    opened by jiruhameru 4
  • Parallel BigCLAM Gradient Computation

    Parallel BigCLAM Gradient Computation


    I've noticed that the gradient calculation in BigCLAM could be easily parallelized. This should be embarrassingly parallel, doing batches no n_jobs gradient calculation. The only issue would be when some node in the batch is also the neighbor of another node in the same batch, since self._do_updates would have to wait for the entire batch to run and then update the duplicated node embeddings.

    This event may be rare if we consider that the graph is sparse and it is unlikely that such "collision" would happen, still, if it did happen, i believe it would not be a huge problem, as long as it does not happen in further iterations (which is even more unlikely)

    What do you guys think? I could implement this if you think it'd be safe to incur in the issue i've mentioned above.

    opened by AlanGanem 2
  • Randomness in Laplacian Eigenmaps Embeddings

    Randomness in Laplacian Eigenmaps Embeddings

    Hi! I'm using Laplacian Eigenmaps and noticed that the resulting embeddings are not always the same, even though I have explicitly set the seed:

    model = LaplacianEigenmaps(dimensions=3,seed=0)

    Running the same algorithm in the same python session for multiple times yields different embeddings each time. Here is a minimal reproducible example:

    import networkx as nx
    g_undirected = nx.newman_watts_strogatz_graph(1000, 20, 0.05, seed=1)
    from karateclub.node_embedding.neighbourhood import LaplacianEigenmaps
    import numpy as np
    for _ in range(5):
        model = LaplacianEigenmaps(dimensions=3,seed=0)
        node_emb_le = model.get_embedding()

    It yields the following summed value of the embeddings for me:


    How can I control the randomness so that every time the resulting embeddings are exactly the same, even if I run the algorithm for arbitrary times in the same python session?

    opened by wendywangwwt 1
Benedek Rozemberczki
PhD candidate at The University of Edinburgh @cdt-data-science working on machine learning and data mining related to graph structured data.
Benedek Rozemberczki
A lightweight interface for reading in output from the Weather Research and Forecasting (WRF) model into xarray Dataset

xwrf A lightweight interface for reading in output from the Weather Research and Forecasting (WRF) model into xarray Dataset. The primary objective of

National Center for Atmospheric Research 43 Nov 29, 2022
ped-crash-techvol: Texas Ped Crash Tech Volume Pack

ped-crash-techvol: Texas Ped Crash Tech Volume Pack In conjunction with the Final Report "Identifying Risk Factors that Lead to Increase in Fatal Pede

Network Modeling Center; Center for Transportation Research; The University of Texas at Austin 2 Sep 28, 2022
A DSL for data-driven computational pipelines

"Dataflow variables are spectacularly expressive in concurrent programming" Henri E. Bal , Jennifer G. Steiner , Andrew S. Tanenbaum Quick overview Ne

1.9k Jan 03, 2023
A set of procedures that can realize covid19 virus detection based on blood.

A set of procedures that can realize covid19 virus detection based on blood.

Nuyoah-xlh 3 Mar 07, 2022
Shot notebooks resuming the main functions of GeoPandas

Shot notebooks resuming the main functions of GeoPandas, 2 notebooks written as Exercises to apply these functions.

1 Jan 12, 2022
A powerful data analysis package based on mathematical step functions. Strongly aligned with pandas.

The leading use-case for the staircase package is for the creation and analysis of step functions. Pretty exciting huh. But don't hit the close button

48 Dec 21, 2022
Python package to transfer data in a fast, reliable, and packetized form.

pySerialTransfer Python package to transfer data in a fast, reliable, and packetized form.

PB2 101 Dec 07, 2022
Larch: Applications and Python Library for Data Analysis of X-ray Absorption Spectroscopy (XAS, XANES, XAFS, EXAFS), X-ray Fluorescence (XRF) Spectroscopy and Imaging

Larch: Data Analysis Tools for X-ray Spectroscopy and More Documentation: http://xraypy.github.io/xraylarch Code: http://github.com/xraypy/xraylarch L

xraypy 95 Dec 13, 2022
MoRecon - A tool for reconstructing missing frames in motion capture data.

MoRecon - A tool for reconstructing missing frames in motion capture data.

Yuki Nishidate 38 Dec 03, 2022
Candlestick Pattern Recognition with Python and TA-Lib

Candlestick-Pattern-Recognition-with-Python-and-TA-Lib Goal Look at the S&P500 to try and get a better understanding of these candlestick patterns and

Ganesh Jainarain 11 Oct 07, 2022
BioMASS - A Python Framework for Modeling and Analysis of Signaling Systems

Mathematical modeling is a powerful method for the analysis of complex biological systems. Although there are many researches devoted on produ

BioMASS 22 Dec 27, 2022
Powerful, efficient particle trajectory analysis in scientific Python.

freud Overview The freud Python library provides a simple, flexible, powerful set of tools for analyzing trajectories obtained from molecular dynamics

Glotzer Group 195 Dec 20, 2022
Methylation/modified base calling separated from basecalling.

Remora Methylation/modified base calling separated from basecalling. Remora primarily provides an API to call modified bases for basecaller programs s

Oxford Nanopore Technologies 72 Jan 05, 2023
This repo is dedicated to the data extraction and manipulation of the World Bank's database called STEP.

Overview Welcome to the Step-X repository. This repo is dedicated to the data extraction and manipulation of the World Bank's database called STEP. Be

Keanu Pang 0 Jan 20, 2022
A tool to compare differences between dataframes and create a differences report in Excel

similarpanda A module to check for differences between pandas Dataframes, and generate a report in Excel format. This is helpful in a workplace settin

Andre Pretorius 9 Sep 15, 2022
A Python package for the mathematical modeling of infectious diseases via compartmental models

A Python package for the mathematical modeling of infectious diseases via compartmental models. Originally designed for epidemiologists, epispot can be adapted for almost any type of modeling scenari

epispot 12 Dec 28, 2022
Collections of pydantic models

pydantic-collections The pydantic-collections package provides BaseCollectionModel class that allows you to manipulate collections of pydantic models

Roman Snegirev 20 Dec 26, 2022
Exploratory Data Analysis of the 2019 Indian General Elections using a dataset from Kaggle.

2019-indian-election-eda Exploratory Data Analysis of the 2019 Indian General Elections using a dataset from Kaggle. This project is a part of the Cou

Souradeep Banerjee 5 Oct 10, 2022
Scraping and analysis of leetcode-compensations page.

Leetcode compensations report Scraping and analysis of leetcode-compensations page.

utsav 96 Jan 01, 2023
Analytical view of olist e-commerce in Brazil

Analysis of E-Commerce Public Dataset by Olist The objective of this project is to propose an analytical view of olist e-commerce in Brazil. For this

Gurpreet Singh 1 Jan 11, 2022