Giter Club home page Giter Club logo

architecturemattersgcl's Introduction

Introduction

We observe that common phenomena among existing GCL methods that are quite different from VCL methods, including 1) positive samples are not a must for GCL; 2) negative samples are not necessary for graph classification, neither for node classification when adopting specific normalization modules; 3) data augmentations have much less influence on GCL, as simple domain-agnostic augmentations (e.g., Gaussian noise) can also attain fairly good performance. By uncovering how the implicit inductive bias of GNNs works in contrastive learning, we theoretically provide insights into the above intriguing properties of GCL.

File Structures

We provide implementations of GCL methods including GRACE, GCA, ProGCL, AutoGCL, BGRL, GraphCL, JOAO, ADGCL, InfoGraph, and a VCL method SimCLR. For running details, please refer to the README.md file in the corresponding sub-directory.

ContraNorm/
├── README.md
├── GCL/
│   ├── README.md
│   ├── ADGCL/ 
│   │   ├── README.md
│   │   └── ...
│   ├── AutoGCL/
│   │   ├── README.md
│   │   └── ...
│   ├── BGRL/
│   │   ├── README.md
│   │   └── ...
│   ├── GCA/
│   │   ├── README.md
│   │   └── ...
│   ├── GRACE/
│   │   ├── README.md
│   │   └── ...
│   ├── GraphCL/
│   │   ├── README.md
│   │   └── ...
│   ├── InfoGraph/
│   │   ├── README.md
│   │   └── ...
│   ├── ProGCL/
│   │   ├── README.md
│   │   └── ...
│   ├── JOAO/
│   │   ├── README.md
│   │   └── ...
│   └── datasets/
├── VCL/
│   ├── README.md
│   └── ...
└── ...

Citation

If you use our code, please cite

@inproceedings{guo2023architecture,
  title={Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning},
  author={Xiaojun Guo and Yifei Wang and Zeming Wei and Yisen Wang},
  booktitle={NeurIPS},
  year={2023}
}

architecturemattersgcl's People

Contributors

guoxiaojun1999 avatar

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.