gongchenghua/Papers-Graphs-with-Heterophily

A Survey of Learning from Graphs with Heterophily

25
/ 100
Experimental

This project offers a curated collection of over 500 research papers focused on 'heterophily' in graph-based machine learning. It helps researchers, PhD students, and data scientists quickly find relevant literature on how to analyze and learn from complex networks where connected entities are often dissimilar. You get an organized list of papers from top conferences, categorized by year, to stay current with advancements in this field.

160 stars. No commits in the last 6 months.

Use this if you are a researcher or practitioner in machine learning or network science and need to understand the latest methods for handling graphs where connected nodes have different characteristics.

Not ideal if you are looking for an introduction to graph theory or basic graph machine learning, as this resource assumes familiarity with these concepts and focuses on a very specific research topic.

network-science machine-learning-research graph-analytics academic-literature data-science
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

160

Forks

5

Language

License

Last pushed

Feb 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gongchenghua/Papers-Graphs-with-Heterophily"

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