Giter Club home page Giter Club logo

gcn-benchmark's Introduction

Graph Convolution Networks Benchmarks

In This project i tested gcn in a bunch of ML Tasks

  • Node Classification
  • The impact of GCN Depth/Width on accuracy
  • Apply Transfer Learning on Node Classification
  • Visualize K-hops neighbors in Graphs

Project Requirements

  • torch
  • dgl
  • wandb
  • matplotlib
  • numpy

Node Classification Test

Cora Dataset

  • Nodes: 2708
  • Edges: 10556
  • Graph Diameter: 20
  • Node Features: 1433
  • Num Classes: 7

Pubmed Dataset

  • Nodes: 19717
  • Edges: 88651
  • Graph Diameter: 3.7 ~ 4 (90-percentile effective diameter)
  • Node Features: 500
  • Num Classes: 3

What each node in GNN see with K layers

2 Layer GCN

2 layer GNN

10 Layer GCN

10 layer GNN

Over Smoothing problem in GNNs

depth_diameter

GCN Width Vs Accuracy

width_accuracy

Feature transformation in GCN

features_tsne

Block Based GCN Vs Flat GCN

GNN Blocks Design

gnn_blocks

flat_vs_bloc_acc flat_vs_bloc_test_loss

References

@misc{kipf2017semisupervised,
      title={Semi-Supervised Classification with Graph Convolutional Networks}, 
      author={Thomas N. Kipf and Max Welling},
      year={2017},
      eprint={1609.02907},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{wandb,
title = {Experiment Tracking with Weights and Biases},
year = {2020},
note = {Software available from wandb.com},
url={https://www.wandb.com/},
author = {Biewald, Lukas},
}

@misc{wang2020deep,
      title={Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks}, 
      author={Minjie Wang and Da Zheng and Zihao Ye and Quan Gan and Mufei Li and Xiang Song and Jinjing Zhou and Chao Ma and Lingfan Yu and Yu Gai and Tianjun Xiao and Tong He and George Karypis and Jinyang Li and Zheng Zhang},
      year={2020},
      eprint={1909.01315},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

gcn-benchmark's People

Contributors

abidikhairi avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.