# LirongWu/awesome-graph-self-supervised-learning

Code for TKDE paper "Self-supervised learning on graphs: Contrastive, generative, or predictive"

Repository: https://github.com/LirongWu/awesome-graph-self-supervised-learning
Canonical: https://ross.abutalabs.com/products/awesome-graph-self-supervised-learning
License Family: other
Topics: self-supervised-learning, machine-learning, unsupervised-learning, graph-neural-networks, pre-training, data-augmentation, pretext-task, representation-learning, transfer-learning, deep-learning
Last push: 2024-08-15T07:29:45+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2658, "days_push": 748, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1436, forks 166 (observed 2026-08-28T04:04:43.527168+00:00)

## What it is
A curated awesome-list of papers, code, and datasets for self-supervised learning on graphs, accompanying a TKDE survey paper. It organizes methods into contrastive, generative, and predictive categories with summaries of implementations and common graph datasets.

## Use cases
- find papers on self-supervised learning for graphs
- compare contrastive vs generative graph pre-training methods
- find open-source implementations of graph SSL methods
- find common graph datasets for representation learning benchmarks
- learn about graph neural network pre-training techniques
- get started with unsupervised learning on graph-structured data

## When to choose
- you need a survey-style entry point into graph self-supervised learning research
- you want a categorized reading list with linked code and datasets
- you are writing a literature review on graph representation learning

## When to avoid
- you need a production-ready library or framework to train models
- you want maintained, runnable code rather than paper links
- you need non-graph self-supervised learning resources

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, tutorials
- platform: python
- tags: awesome-list, graph-neural-networks, self-supervised-learning, representation-learning, graph-contrastive-learning, pre-training, survey

## Member repositories
- LirongWu/awesome-graph-self-supervised-learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.527168+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:36:46.005229+00:00, confidence not recorded.
  - readme: https://github.com/LirongWu/awesome-graph-self-supervised-learning (fetched 2026-08-28T04:04:43.527168+00:00, sha 198505940759)
- Data as of 2026-08-30T08:39:29.467469+00:00.