Home

Awesome

Awesome Self-Supervised Learning for Graphs

Awesome GitHub stars GitHub forks visitors

A curated list for awesome self-supervised graph representation learning resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers, awesome-architecture-search, and awesome-self-supervised-learning.

Background

Self-supervised learning is the future! — Yann LeCun

Recently self-supervised learning (SSL) techniques have gained success in many domains, e.g., visual, natural language processing, and robotics, where SSL methods even outperform their supervised counterparts. However, the development of SSL in the graph domain is still at a nascent stage. Can SSL graph representation achieve similar or even better performance than its supervised opponents? This repository provides you with a curated list of awesome self-supervised graph representation learning resources. Following [Ankesh Anand 2020], we roughly divide papers into two lines: generative/predictive (i.e. optimizing in the output space) and contrastive methods (i.e. optimizing in the latent space). Along with papers, we also list several must-read blog posts and talks.

Contribution

Feel free to send pull requests to add more links!

Table of Contents

Papers

Surveys

Generative/Predictive Methods

Year 2020

Contrastive Methods

Year 2021

Year 2020

Year 2019

Applications

Blog Posts

Talks