Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
Full Changelog: https://github.com/benedekrozemberczki/karateclub/compare/v_10303...v_10304
Full Changelog: https://github.com/benedekrozemberczki/karateclub/compare/v_10302...v_10303
Full Changelog: https://github.com/benedekrozemberczki/karateclub/compare/v_10301...v_10302
maximum_number_of_iterations
by @LucaCappelletti94 in https://github.com/benedekrozemberczki/karateclub/pull/106
Full Changelog: https://github.com/benedekrozemberczki/karateclub/compare/v_10300...v_10301
The release adds vector induction (inference) for all of the graph level embedding methods. Including:
Graph2Vec GL2Vec
Full Changelog: https://github.com/benedekrozemberczki/karateclub/compare/v_10203...v_10204
Added Wavelet Characteristic from the CIKM 2021 paper: Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization
The new release supports directed and disjoint graphs: