STAR-Laboratory/Accelerating-RecSys-Training
Accelerating Recommender model training by leveraging popular choices -- VLDB 2022
This project helps e-commerce or content platforms quickly train their recommendation systems. By taking historical user interaction data, it produces a model that predicts what items a user is likely to click on next. This tool is designed for data scientists or machine learning engineers responsible for building and optimizing recommendation engines.
No commits in the last 6 months.
Use this if you need to significantly speed up the training process for large-scale click-through rate prediction models on datasets like Criteo, especially when dealing with popular items.
Not ideal if you are looking for a recommendation system for small datasets or don't have access to GPU resources, as the primary benefits are seen with large-scale, accelerated training.
Stars
31
Forks
4
Language
Python
License
MIT
Category
Last pushed
Sep 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/STAR-Laboratory/Accelerating-RecSys-Training"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
meta-pytorch/torchrec
Pytorch domain library for recommendation systems
recommenders-team/recommenders
Best Practices on Recommendation Systems
hongleizhang/RSPapers
RSTutorials: A Curated List of Must-read Papers on Recommender System.
kakao/buffalo
TOROS Buffalo: A fast and scalable production-ready open source project for recommender systems
google-research/recsim
A Configurable Recommender Systems Simulation Platform