Giter VIP home page Giter VIP logo

gnas-mp's Introduction

🔥News🔥

Hi, if you like this work, you may be interested in our new work, too.

Welcome to our latest work Automatic Relation-aware Graph Network Proliferation.

This work has been accepted by CVPR2022 and selected as an ORAL presentation.

In the latest work, we have achieved state-of-the-art results on SBM_CLUSTER (77.35% OA), ZINC_100k (0.136 MAE), CIFAR10 (73.90% OA), TSP (0.855 F1-score) datasets and so on.

What's new?

  1. We devise a novel dual relation-aware graph search space that comprises both node and relation learning operations. So, the ARGNP can leverage the edge attributes in some datasets, such as ZINC. It significantly improves the graph representative capability. Interestingly, we also observe the performance improvement even if there is no available edge attributes in some datasets.

  2. We design a network proliferation search paradigm (NPSP) to progressively determine the GNN architectures by iteratively performing network division and differentiation. The network proliferation search paradigm decomposes the training of global supernet into sequential local supernets optimization, which alleviates the interference among child graph neural architectures. It reduces the spatial-time complexity from quadratic to linear and enables the search to thoroughly free from the cell-sharing trick.

  3. Our framework is suitable for solving node-level, edge-level, and graph-level tasks. The codes are easy to use.


Rethinking Graph Neural Architecture Search from Message-passing

Getting Started

0. Prerequisites

  • Linux
  • NVIDIA GPU + CUDA CuDNN

1. Setup Python Environment

# clone Github repo
conda install git
git clone https://github.com/phython96/GNAS-MP.git
cd GNAS-MP

# Install python environment
conda env create -f environment_gpu.yml
conda activate gnasmp

2. Download datasets

The datasets are provided by project benchmarking-gnns, you can click here to download all the required datasets.

3. Search Architectures

sh scripts/search_molecules_zinc.sh [gpu_id]

4. Train & Test

sh scripts/train_molecules_zinc.sh [gpu_id] '[path_to_genotypes]/example.yaml'

Reference

@inproceedings{cai2021rethinking,
  title={Rethinking Graph Neural Architecture Search from Message-passing},
  author={Cai, Shaofei and Li, Liang and Deng, Jincan and Zhang, Beichen and Zha, Zheng-Jun and Su, Li and Huang, Qingming},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={6657--6666},
  year={2021}
}

gnas-mp's People

Contributors

phython96 avatar

Forkers

xuechendi

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.