cleora VS GEM

Our team at Synerise AI has open sourced Cleora - an ultra fast vertex embedding tool for graphs & hypergraphs. If you've ever used node2vec, DeepWalk, LINE or similar methods - it might be worth to check it out.

A few weeks ago, our team at Synerise AI has open sourced Cleora - an ultra fast vertex embedding tool for graphs & hypergraphs. It is a tool, which can ingest any categorical, relational data and turn it into vector embeddings of entities. It is extremely fast, while offering very competitive quality of results. In fact, it may be the fastest hypergraph embedding tool possible in practice, without intentionally discarding/reducing input data.

Thanks for raising so many interesting points about model performance and complexity. In this context, I think our newly released graph embedding library - Cleora - might be of interest: https://github.com/Synerise/cleora Cleora has some nice performance-wise properties:

Synerise/cleora (Rust): Cleora AI is a general-purpose model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data.

Besides, they implemented a fast C++ version of the code that works for much larger graphs. If one searches for ProNE's implementation, they would (hypothetically) find the scikit-style wrapper instead of the fully-functional release. It reminds me of a situation with HOPE, when authors of one survey "implemented" it as naive SVD (https://github.com/palash1992/GEM/blob/master/gem/embedding/hope.py#L68) instead of Jacobi-Davidson generalized solver described in the paper (and literally with code released!!). In the end, I would assume that poor paper was less cited because of that repackaging effort.