Implementation of Graph Neural Tangent Kernel (NeurIPS 2019)
Alternatives To Gntk
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
2 days ago1March 03, 2021150Perl
Stack trace visualizer
7 years ago1
图解tensorflow 源码
a year ago1gpl-3.0Python
A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).
Grakel50216 months ago5September 09, 20196otherPython
A scikit-learn compatible library for graph kernels
Kokkos Kernels238
21 hours ago235otherC++
Kokkos C++ Performance Portability Programming EcoSystem: Math Kernels - Provides BLAS, Sparse BLAS and Graph Kernels
7 months ago11mitCython
A graph matching library for Python
a year ago2mitPython
The source codes for Fine-grained Fact Verification with Kernel Graph Attention Network.
5 years agomitMATLAB
Code for "M. Zhang, Z. Cui, M. Neumann, and Y. Chen, An End-to-End Deep Learning Architecture for Graph Classification, AAAI-18".
a month ago3gpl-3.0C++
This is a tool for Linux kernel ftrace and perf events visualization
Assignment2 2018111
5 years agoPython
(Spring 2018) Assignment 2: Graph Executor with TVM
Alternatives To Gntk
Select To Compare

Alternative Project Comparisons

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

This repository implements Graph Neural Tangent Kernel (infinitely wide multi-layer GNNs trained by gradient descent), described in the following paper:

Simon S. Du, Kangcheng Hou, Barnabás Póczos, Ruslan Salakhutdinov, Ruosong Wang, Keyulu Xu. Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels. NeurIPS 2019. [arXiv] [Paper]

Test run

Unzip the dataset file


Here we demonstrate how to use GNTK to perform classification on IMDB-BINARY dataset. We set the number of BLOCK operations to be 2, the number of MLP layers to be 2 and c_u to be 1.

Compute the GNTK gram matrix

mkdir out
python --dataset IMDBBINARY --num_mlp_layers 2 --num_layers 2 --scale uniform --jk 1 --out_dir out

Classification with kernel regression

python --data_dir ./out --dataset IMDBBINARY

Therefore we get the hyper-parameter search results at ./out/grid_search.csv.

Experiment for all datasets

To run the experiment described in our paper, please run bash and bash in order.

Popular Kernel Projects
Popular Graph Projects
Popular Operating Systems Categories

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Neural Network