SherylHYX/GNNRank

Official code for the ICML2022 paper -- GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks

40
/ 100
Emerging

This project helps you determine a global ranking from many individual comparisons, like ranking sports teams based on game outcomes or products based on user preferences. It takes in datasets of pairwise comparisons and outputs a comprehensive, ordered list. This is useful for anyone needing to establish a definitive hierarchy from a collection of smaller, relative judgments, such as sports analysts, market researchers, or product managers.

No commits in the last 6 months.

Use this if you have a dataset where items are compared against each other in pairs (e.g., A beat B, C is preferred over D) and you need to generate a single, overall ranking of all items.

Not ideal if your data is already in a ranked list format or if you need to perform other types of graph analysis beyond global ranking from pairwise comparisons.

Sports Analytics Preference Modeling Competitive Analysis Ranking Systems Survey Analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

54

Forks

10

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SherylHYX/GNNRank"

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