Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs
This framework addresses the need for accessible and scalable tools for unsupervised graph learning, primarily benefiting machine learning researchers and practitioners, but it is incremental as it packages existing algorithms.
The authors introduced Karate Club, a Python framework that integrates over 30 state-of-the-art graph mining algorithms to solve unsupervised learning tasks, making community detection and graph embeddings accessible to researchers and practitioners. They demonstrated its efficiency with competitive learning performance and speed on real-world clustering and classification problems.
We present Karate Club a Python framework combining more than 30 state-of-the-art graph mining algorithms which can solve unsupervised machine learning tasks. The primary goal of the package is to make community detection, node and whole graph embedding available to a wide audience of machine learning researchers and practitioners. We designed Karate Club with an emphasis on a consistent application interface, scalability, ease of use, sensible out of the box model behaviour, standardized dataset ingestion, and output generation. This paper discusses the design principles behind this framework with practical examples. We show Karate Club's efficiency with respect to learning performance on a wide range of real world clustering problems, classification tasks and support evidence with regards to its competitive speed.