TatsuyaShirakawa/poincare-embedding
Poincaré Embedding (unofficial)
This tool helps researchers and data scientists represent complex hierarchical relationships, like those found in biological taxonomies or organizational charts, in a compact, geometric space. You input structured hierarchical data, such as parent-child relationships, and it outputs numerical embeddings that capture these hierarchies. This is ideal for anyone working with data that naturally forms a tree-like structure.
229 stars. No commits in the last 6 months.
Use this if you need to map hierarchical data into a continuous, low-dimensional space for visualization, classification, or other analytical tasks.
Not ideal if your data lacks clear hierarchical structure or if you primarily need to analyze flat, non-relational datasets.
Stars
229
Forks
28
Language
C++
License
MIT
Category
Last pushed
May 07, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TatsuyaShirakawa/poincare-embedding"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zeiss-microscopy/OAD
Collection of tools and scripts useful to automate microscopy workflows in ZEN Blue using Python...
median-research-group/LibMTL
A PyTorch Library for Multi-Task Learning
qdrant/quaterion
Blazing fast framework for fine-tuning similarity learning models
lucidrains/PoPE-pytorch
Efficient implementation (and explorations) into polar coordinate positional embedding (PoPE) -...
MR-HosseinzadehTaher/BenchmarkTransferLearning
Official PyTorch Implementation and Pre-trained Models for Benchmarking Transfer Learning for...