Martin-qyma/HERec
"Breaking Information Cocoons: A Hyperbolic Graph-LLM Framework for Exploration and Exploitation in Recommender Systems"
This project helps e-commerce managers and content curators improve their recommendation systems. It takes in existing user-item interaction data and item descriptions to generate smarter recommendations. The output is a list of recommended items for users that better balances showing familiar items with introducing new, relevant ones, helping users discover more and avoid seeing only the same types of products.
No commits in the last 6 months.
Use this if you manage an online platform and want to break users out of 'information cocoons' by improving both the relevance and diversity of your recommendations.
Not ideal if you need a plug-and-play recommendation solution without the need for fine-tuning or managing underlying model components.
Stars
12
Forks
—
Language
Python
License
—
Category
Last pushed
Jan 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Martin-qyma/HERec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
snap-research/GRID
GRID: Generative Recommendation with Semantic IDs
eugeneyan/semantic-ids-llm
Semantic IDs: How to train an LLM-Recommender Hybrid with steerability and reasoning on recommendations.
HKUDS/XRec
[EMNLP'2024] "XRec: Large Language Models for Explainable Recommendation"
HKUDS/RLMRec
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
HKUDS/EasyRec
[EMNLP'2025] "EasyRec: Simple yet Effective Language Model for Recommendation"