ucbrise/graphtrans
Representing Long-Range Context for Graph Neural Networks with Global Attention
This project offers PyTorch code for researchers and machine learning engineers working on graph neural networks. It helps improve how these networks capture long-range relationships within complex graph data, such as molecular structures or code dependencies. By providing an advanced architecture, it takes existing graph datasets and outputs enhanced model performance metrics, particularly useful for tasks like molecular property prediction or code analysis.
136 stars. No commits in the last 6 months.
Use this if you are a researcher or machine learning engineer developing or evaluating advanced graph neural network architectures and need to improve their ability to process global context in graph-structured data.
Not ideal if you are looking for a high-level API for everyday graph analysis or do not have experience with PyTorch and deep learning model development.
Stars
136
Forks
21
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ucbrise/graphtrans"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.