snap-research/graphless-neural-networks
[ICLR 2022] Code for Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation (GLNN)
This project offers a way to classify items in interconnected datasets, like academic papers linked by citations or products linked by co-purchases. It takes your existing connected data and, through a process called distillation, outputs a simpler model that can classify new items almost as accurately as complex models, but much faster. Data scientists and machine learning engineers who work with graph-structured data will find this useful for deploying efficient classification systems.
No commits in the last 6 months.
Use this if you need to build a machine learning model that classifies items in a network (like documents or products) and you prioritize faster prediction speeds without sacrificing much accuracy.
Not ideal if you primarily need to develop entirely new graph neural network architectures from scratch or if maximum classification accuracy at any computational cost is your absolute top priority.
Stars
95
Forks
21
Language
Python
License
MIT
Category
Last pushed
Oct 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/snap-research/graphless-neural-networks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.