HKUDS/RecDiff

[CIKM'2024] "RecDiff: Diffusion Model for Social Recommendation"

36
/ 100
Emerging

This project helps e-commerce platforms, social media apps, and content providers give better product, content, or connection recommendations to their users. It takes existing user interaction data and social connections, identifies and removes 'noisy' or unhelpful social ties, and then outputs more accurate and relevant personalized recommendations. Social media managers, product recommendation specialists, and platform growth strategists would find this valuable.

No commits in the last 6 months.

Use this if your social recommendation system struggles with inaccurate suggestions due to irrelevant or misleading social connections among users.

Not ideal if your recommendation system doesn't rely on social connections, or if you need a solution for a purely cold-start recommendation problem without existing social graphs.

social-commerce personalized-marketing content-discovery social-network-analysis e-commerce-recommendations
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

89

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jun 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HKUDS/RecDiff"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.