ssnl/poisson_quasimetric_embedding
Open source code for paper "On the Learning and Learnability of Quasimetrics".
This project offers a method to calculate 'one-way' distances between items or concepts, where the distance from A to B isn't necessarily the same as B to A. It takes in numerical representations (latent vectors) of these items and outputs their asymmetrical distances. This is useful for researchers and data scientists working with complex relationships, like those found in social networks or sequential decision-making.
No commits in the last 6 months.
Use this if you need to measure directional relationships, such as the cost of transitioning from state A to state B in a system, which might be different from transitioning from B to A.
Not ideal if your problem assumes symmetrical distances where the 'distance' between two items is always the same regardless of direction.
Stars
32
Forks
1
Language
C++
License
BSD-3-Clause
Category
Last pushed
Nov 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ssnl/poisson_quasimetric_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...