Skip to content

Note : need to update this repo since there's lot of recent changes.

License

Notifications You must be signed in to change notification settings

konan009/Quantization-of-Graph-Neural-Networks

Repository files navigation

Note : need to update this repo since there's lot of recent changes.

Quantization of Graph Neural Network

Quantization for deep learning is the process of approximating a neural network that uses floating-point numbers by a neural network of low bit width numbers. This dramatically reduces both the memory requirement and computational cost of using neural networks.

Graph Neural Networks (GNNs) on the other hand, is a class of deep learning methods designed to perform inference on data described by graphs. GNNs are neural networks that can be directly applied to graphs, and provide an easy way to do node-level, edge-level, and graph-level prediction tasks

The accuracy result is below here :

For more information you can check the paper in the repository that is in PDF format.

About

Note : need to update this repo since there's lot of recent changes.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published