qitianwu/DIFFormer

The official implementation for ICLR23 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"

34
/ 100
Emerging

This tool helps data scientists and machine learning engineers analyze complex data by creating meaningful representations from various inputs like individual data points, interconnected networks (graphs), or even batches of multiple networks. It takes raw data, such as features of objects or their relationships, and processes them to output enhanced numerical descriptions which can then be used for tasks like classification or prediction.

313 stars. No commits in the last 6 months.

Use this if you need to generate high-quality data representations for machine learning models, especially when dealing with large datasets or data that naturally forms a network structure.

Not ideal if your primary goal is simple data aggregation or if you are not working with machine learning models that benefit from advanced feature representations.

data representation graph analytics machine learning engineering predictive modeling feature extraction
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

313

Forks

28

Language

Python

License

Last pushed

Jul 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/qitianwu/DIFFormer"

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