# Self-supervised Learning on Graphs: Deep Insights and New Direction

arXiv: https://arxiv.org/abs/2006.10141 · HTML: https://mlsanity.com/paper/2006.10141/

## Key facts

- Cited by 108 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 30 of 108)

- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Graph Contrastive Learning Automated](https://mlsanity.com/paper/2106.07594/) (2021)
- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [All in One: Multi-task Prompting for Graph Neural Networks](https://mlsanity.com/paper/2307.01504/) (2023)
- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks](https://mlsanity.com/paper/2102.05034/) (2021)
- [Universal Prompt Tuning for Graph Neural Networks](https://mlsanity.com/paper/2209.15240/) (2022)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [DIG: A Turnkey Library for Diving into Graph Deep Learning Research](https://mlsanity.com/paper/2103.12608/) (2021)
- [Towards Self-Explainable Graph Neural Network](https://mlsanity.com/paper/2108.12055/) (2021)
- [Graph-MLP: Node Classification without Message Passing in Graph](https://mlsanity.com/paper/2106.04051/) (2021)
- [FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning](https://mlsanity.com/paper/2104.14210/) (2021)
- [Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels](https://mlsanity.com/paper/2201.00232/) (2022)
- [Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage](https://mlsanity.com/paper/2206.03426/) (2022)
- [Graph-based Molecular Representation Learning](https://mlsanity.com/paper/2207.04869/) (2022)
- [Automated Self-Supervised Learning for Graphs](https://mlsanity.com/paper/2106.05470/) (2021)
- [Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment](https://mlsanity.com/paper/2502.02017/) (2025)
- [Spectral Augmentation for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2210.00643/) (2022)
- [GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction](https://mlsanity.com/paper/2106.11133/) (2021)
- [Tree Decomposed Graph Neural Network](https://mlsanity.com/paper/2108.11022/) (2021)
- [SGL-PT: A Strong Graph Learner with Graph Prompt Tuning](https://mlsanity.com/paper/2302.12449/) (2023)
- [SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving](https://mlsanity.com/paper/2206.14116/) (2022)
- [Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees](https://mlsanity.com/paper/2412.16441/) (2024)
- [Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2104.07917/) (2021)
- [Adaptive Transfer Learning on Graph Neural Networks](https://mlsanity.com/paper/2107.08765/) (2021)
- [MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization](https://mlsanity.com/paper/2210.00102/) (2022)
- [Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative](https://mlsanity.com/paper/2210.03801/) (2022)
- [Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations](https://mlsanity.com/paper/2201.01702/) (2022)
- [MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2201.02534/) (2022)

## Abstract (arXiv)

The success of deep learning notoriously requires larger amounts of costly annotated data. This has led to the development of self-supervised learning (SSL) that aims to alleviate this limitation by creating domain specific pretext tasks on unlabeled data. Simultaneously, there are increasing interests in generalizing deep learning to the graph domain in the form of graph neural networks (GNNs). GNNs can naturally utilize unlabeled nodes through the simple neighborhood aggregation that is unable to thoroughly make use of unlabeled nodes. Thus, we seek to harness SSL for GNNs to fully exploit the unlabeled data. Different from data instances in the image and text domains, nodes in graphs present unique structure information and they are inherently linked indicating not independent and identically distributed (or i.i.d.). Such complexity is a double-edged sword for SSL on graphs. On the one hand, it determines that it is challenging to adopt solutions from the image and text domains to graphs and dedicated efforts are desired. On the other hand, it provides rich information that enables us to build SSL from a variety of perspectives. Thus, in this paper, we first deepen our understandings on when, why, and which strategies of SSL work with GNNs by empirically studying numerous basic SSL pretext tasks on graphs. Inspired by deep insights from the empirical studies, we propose a new direction SelfTask to build advanced pretext tasks that are able to achieve state-of-the-art performance on various real-world datasets. The specific experimental settings to reproduce our results can be found in urlhttps://github.com/ChandlerBang/SelfTask-GNN.