allegro/allRank
allRank is a framework for training learning-to-rank neural models based on PyTorch.
This framework helps machine learning practitioners develop and experiment with neural network models for ranking tasks. It takes structured data, typically in libsvm format, where items are associated with a relevance score, and outputs a trained model that can sort new items by predicted relevance. Data scientists, machine learning engineers, and researchers can use this to build customized ranking systems for search, recommendations, or content personalization.
994 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need a flexible toolkit to build, train, and evaluate custom learning-to-rank neural models with various loss functions and architectures.
Not ideal if you are looking for an out-of-the-box solution without deep customization, or if you don't have experience with machine learning model development.
Stars
994
Forks
127
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 06, 2024
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/allegro/allRank"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
oracle/tribuo
Tribuo - A Java machine learning library
o19s/elasticsearch-learning-to-rank
Plugin to integrate Learning to Rank (aka machine learning for better relevance) with Elasticsearch
Waikato/meka
Multi-label classifiers and evaluation procedures using the Weka machine learning framework.
Waikato/moa
MOA is an open source framework for Big Data stream mining. It includes a collection of machine...
punit-naik/MLHadoop
This repository contains Machine-Learning MapReduce codes for Hadoop which are written from...