karateclub: A Python repository from Cortys

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.

Citing

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

@inproceedings{karateclub,
       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)

splitter.fit(g)

print(splitter.get_memberships())

Models included

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

Overlapping Community Detection

DANMF from Ye et al.: Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection (CIKM 2018)
M-NMF from Wang et al.: Community Preserving Network Embedding (AAAI 2017)
Ego-Splitting from Epasto et al.: Ego-splitting Framework: from Non-Overlapping to Overlapping Clusters (KDD 2017)
NNSED from Sun et al.: A Non-negative Symmetric Encoder-Decoder Approach for Community Detection (CIKM 2017)
BigClam from Yang and Leskovec: Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach (WSDM 2013)
SymmNMF from Kuang et al.: Symmetric Nonnegative Matrix Factorization for Graph Clustering (SDM 2012)

Non-Overlapping Community Detection

GEMSEC from Rozemberczki et al.: GEMSEC: Graph Embedding with Self Clustering (ASONAM 2019)
EdMot from Li et al.: EdMot: An Edge Enhancement Approach for Motif-aware Community Detection (KDD 2019)
SCD from Prat-Perez et al.: High Quality, Scalable and Parallel Community Detectionfor Large Real Graphs (WWW 2014)
Label Propagation from Raghavan et al.: Near Linear Time Algorithm to Detect Community Structures in Large-Scale Networks (Physics Review E 2007)

Neighbourhood-Based Node Level Embedding

GLEE from Torres et al.: GLEE: Geometric Laplacian Eigenmap Embedding (Journal of Complex Networks 2020)
BoostNE from Li et al.: Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximation (ASONAM 2019)
NodeSketch from Yang et al.: NodeSketch: Highly-Efficient Graph Embeddings via Recursive Sketching (KDD 2019)
Diff2Vec from Rozemberczki and Sarkar: Fast Sequence Based Embedding with Diffusion Graphs (CompleNet 2018)
NetMF from Qiu et al.: Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and Node2Vec (WSDM 2018)
RandNE from Zhang et al.: Billion-scale Network Embedding with Iterative Random Projection (ICDM 2018)
Walklets from Perozzi et al.: Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings (ASONAM 2017)
HOPE from Ou et al.: Asymmetric Transitivity Preserving Graph Embedding (KDD 2016)
GraRep from Cao et al.: GraRep: Learning Graph Representations with Global Structural Information (CIKM 2015)
DeepWalk from Perozzi et al.: DeepWalk: Online Learning of Social Representations (KDD 2014)
Node2Vec from Grover et al.: node2vec: Scalable Feature Learning for Networks (KDD 2016)
NMF-ADMM from Sun and Févotte: Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence (ICASSP 2014)
Laplacian Eigenmaps from Belkin and Niyogi: Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering (NIPS 2001)

Structural Node Level Embedding

GraphWave from Donnat et al.: Learning Structural Node Embeddings via Diffusion Wavelets (KDD 2018)
Role2Vec from Ahmed et al.: Learning Role-based Graph Embeddings (IJCAI StarAI 2018)

Attributed Node Level Embedding

FEATHER-N from Rozemberczki et al.: Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models (CIKM 2020)
AE from Rozemberczki et al.: Multi-Scale Attributed Node Embedding (Arxiv 2019)
MUSAE from Rozemberczki et al.: Multi-Scale Attributed Node Embedding (Arxiv 2019)
FSCNMF from Bandyopadhyay et al.: Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks (ArXiV 2018)
SINE from Zhang et al.: SINE: Scalable Incomplete Network Embedding (ICDM 2018)
BANE from Yang et al.: Binarized Attributed Network Embedding (ICDM 2018)
TENE from Yang et al.: Enhanced Network Embedding with Text Information (ICPR 2018)
ASNE from Liao et al.: Attributed Social Network Embedding (TKDE 2018)
TADW from Yang et al.: Network Representation Learning with Rich Text Information (IJCAI 2015)

Meta Node Embedding

NEU from Yang et al.: Fast Network Embedding Enhancement via High Order Proximity Approximation (IJCAI 2017)

Graph Level Embedding

FEATHER-G from Rozemberczki et al.: Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models (CIKM 2020)
IGE from Galland et al.: Invariant Embedding for Graph Classification (ICML 2019 LRGSD Workshop)
LDP from Cai et al.: A Simple Yet Effective Baseline for Non-Attributed Graph Classification (ICLR 2019)
GeoScattering from Gao et al.: Geometric Scattering for Graph Data Analysis (ICML 2019)
GL2Vec from Chen and Koga: GL2Vec: Graph Embedding Enriched by Line Graphs with Edge Features (ICONIP 2019)
NetLSD from Tsitsulin et al.: NetLSD: Hearing the Shape of a Graph (KDD 2018)
SF from de Lara and Pineau: A Simple Baseline Algorithm for Graph Classification (NeurIPS RRL Workshop 2018)
FGSD from Verma and Zhang: Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs (NeurIPS 2017)
Graph2Vec from Narayanan et al.: Graph2Vec: Learning Distributed Representations of Graphs (MLGWorkshop 2017)

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.

Installation

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

License

GNU General Public License v3.0

Cortys/karateclub