Cleora
Active
What is Cleora?
How to use Cleora?
Cleora Core Features
Sparse Markov Matrix
Constructs a sparse transition matrix from your input graph and handles heterogeneous hypergraphs with typed, multi-relational edges natively.
Matrix Powers = All Walk Distributions
Each iteration multiplies the embedding matrix by the sparse transition matrix so M^k captures the full distribution of all walks of length k without sampling or stochastic approximation.
L2-Normalized Propagation
Each iteration replaces every node's embedding with the L2-normalized average of its neighbors' embeddings; 3-4 iterations for co-occurrence similarity and 7+ for contextual similarity.
8 Algorithms, One API
Cleora, ProNE, RandNE, DeepWalk, Node2Vec, HOPE, NetMF, and GraRep are unified under one API with variants for multiscale, attention, directed, weighted, streaming, and inductive graphs.
5 MB, No Heavy Dependencies
The library is about 5 MB with only numpy and scipy required, shipped as a compiled Rust extension with no CUDA or GPU drivers.
Cleora Use Cases
Recommendation systems from user-item bipartite graphs
Fraud detection and anomaly detection on transaction graphs
Social network and knowledge graph embedding at scale
Cleora Frequently Asked Questions
How do I install pycleora?
What dependencies does Cleora require?
Does Cleora require a GPU?
Cleora Product Background & Official Links
Cleora Support Email & Customer service contact & Refund contact etc.
More Contact, visit the about us page(https://cleora.ai/docs)
Cleora Company Info
Cleora Company name: Synerise
More about Cleora, Please visit the about us page(https://cleora.ai/docs)
Cleora GitHub
Cleora GitHub Link: https://github.com/pycleora/pycleora
Cleora Pricing & Plans
Open Source
Free- MIT License
- Install via pip install pycleora
- CPU-only graph embeddings with no GPU required
- Documentation, API reference, and benchmarks included