# Self-supervised Graph Representation Learning via Bootstrapping

arXiv: https://arxiv.org/abs/2011.05126 · HTML: https://mlsanity.com/paper/2011.05126/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Large-Scale Representation Learning on Graphs via Bootstrapping](https://mlsanity.com/paper/2102.06514/) (2021)
- [Graph Barlow Twins: A self-supervised representation learning framework for graphs](https://mlsanity.com/paper/2106.02466/) (2021)
- [Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation](https://mlsanity.com/paper/2201.07986/) (2022)
- [Towards Robust Graph Contrastive Learning](https://mlsanity.com/paper/2102.13085/) (2021)
- [Graph Neural Networks: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2108.10733/) (2021)
- [Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification](https://mlsanity.com/paper/2112.08929/) (2021)
- [Heterogeneous Subgraph Network with Prompt Learning for Interpretable Depression Detection on Social Media](https://mlsanity.com/paper/2407.09019/) (2024)
- [Federated Graph Representation Learning using Self-Supervision](https://mlsanity.com/paper/2210.15120/) (2022)

## Abstract (arXiv)

Graph neural networks~(GNNs) apply deep learning techniques to graph-structured data and have achieved promising performance in graph representation learning. However, existing GNNs rely heavily on enough labels or well-designed negative samples. To address these issues, we propose a new self-supervised graph representation method: deep graph bootstrapping~(DGB). DGB consists of two neural networks: online and target networks, and the input of them are different augmented views of the initial graph. The online network is trained to predict the target network while the target network is updated with a slow-moving average of the online network, which means the online and target networks can learn from each other. As a result, the proposed DGB can learn graph representation without negative examples in an unsupervised manner. In addition, we summarize three kinds of augmentation methods for graph-structured data and apply them to the DGB. Experiments on the benchmark datasets show the DGB performs better than the current state-of-the-art methods and how the augmentation methods affect the performances.