LAGraph VS cleora

> you probably want more specialised tools like BLAS/LAPACK

The GraphBLAS and LAGraph are sparse matrix optimized libraries for this exact purpose:

https://github.com/DrTimothyAldenDavis/GraphBLAS

https://github.com/GraphBLAS/LAGraph/

I work on GraphBLAS, primarily on its LAGraph library and on tutorials. In the last few years, the GraphBLAS community has made a lot of progress on more efficient sparse matrix algorithms and porting graph algorithms to linear algebra – I hope LAGraph can play the role of a more efficient NetworkX in the future. The output of most LAGraph algorithms is a bunch of vectors/matrices so piping these into machine learning algorithms should be possible (and probably more efficient than using other representations).

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.