Lin-Yijie/Graph-Matching-Networks

PyTorch implementation of Graph Matching Networks, e.g., Graph Matching with Bi-level Noisy Correspondence (COMMON, ICCV 2023), Graph Matching Networks for Learning the Similarity of Graph Structured Objects (GMN, ICML 2019).

57
/ 100
Established

This helps researchers in fields like computer vision or bioinformatics determine how similar two complex, graph-structured objects are, even when there's noise or slight variations between them. You provide descriptions of two objects structured as graphs, and it outputs a score indicating their similarity and potentially how their parts correspond. This is for scientists or engineers who work with structured data like molecular graphs, social networks, or image features represented as graphs.

320 stars.

Use this if you need to compare two complex items that can be represented as graphs and find correspondences between their components, especially when facing imperfect or noisy data.

Not ideal if your data is simple, unstructured, or if you only need a basic comparison without detailed correspondence mapping.

graph-comparison pattern-recognition structural-similarity computer-vision bioinformatics
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

320

Forks

60

Language

Python

License

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Lin-Yijie/Graph-Matching-Networks"

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