cleora
node2vec-c
Our great sponsors
cleora | node2vec-c | |
---|---|---|
8 | 1 | |
472 | 50 | |
0.6% | - | |
2.4 | 0.0 | |
6 months ago | almost 4 years ago | |
Jupyter Notebook | C++ | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
cleora
- Cleora - an ultra fast graph embedding tool written in Rust
- Cleora.ai - open source general-purpose model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data - new updates
-
[R] Cleora: A Simple, Strong and Scalable Graph Embedding Scheme
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.
-
[R] Cleora - the fastest graph & hypergraph node embedding tool
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.
-
[D] Why I'm Lukewarm on Graph Neural Networks
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:
-
Rusticles #20 - Wed Nov 18 2020
Synerise/cleora (Rust): Cleora AI is a general-purpose model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data.
node2vec-c
-
[D] Why I'm Lukewarm on Graph Neural Networks
First, I compared the speed (on a 6-core Mac, once, not scientific benchmarking, beware) of your library and a 3 year old standalone implementation I remember I once linked to you when you were posting about your library here (1 year ago? idk) https://github.com/xgfs/node2vec-c . The timings are (wall time) 17min 48s for your library and 4min 34s for the above code. That's (in?)famous Blogcatalog data, since I had that lying around. Note that there is also a node2vec implementation in SNAP and countless more on github. Is there any benchmark showing your version is faster than them?
What are some alternatives?
i3status-rust - Very resourcefriendly and feature-rich replacement for i3status, written in pure Rust
LAGraph - This is a library plus a test harness for collecting algorithms that use the GraphBLAS. For test coverage reports, see https://graphblas.org/LAGraph/ . Documentation: https://lagraph.readthedocs.org
Owlyshield - Owlyshield is an EDR framework designed to safeguard vulnerable applications from potential exploitation (C&C, exfiltration and impact).
GEM
textsynth - A (unofficial) Rust wrapper for the TextSynth API.
finalfusion-rust - finalfusion embeddings in Rust
yourcontrols - Shared cockpit for Microsoft Flight Simulator.
dog - A command-line DNS client.
ggez - Rust library to create a Good Game Easily
PyO3 - Rust bindings for the Python interpreter
Rustlings - :crab: Small exercises to get you used to reading and writing Rust code!