BaseModelAI/cleora
Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team.
Computes all random walks via single matrix multiplication (no negative sampling or approximation), achieving deterministic, reproducible embeddings without GPU requirements. Handles heterogeneous hypergraphs natively through typed TSV input and supports advanced modes including multiscale embeddings, attention-weighted propagation, and supervised refinement. Ships as ~5 MB with unified API supporting nine embedding algorithms (Cleora, ProNE, Node2Vec, DeepWalk, NetMF, etc.) plus built-in tools for community detection, classification, sampling, and compression.
514 stars. No commits in the last 6 months.
Stars
514
Forks
53
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/BaseModelAI/cleora"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
ina-foss/twembeddings
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and...
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics