# Self-supervised Training of Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2006.02380 · HTML: https://mlsanity.com/paper/2006.02380/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [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 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)
- [Towards Self-Explainable Graph Neural Network](https://mlsanity.com/paper/2108.12055/) (2021)
- [Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels](https://mlsanity.com/paper/2201.00232/) (2022)
- [Unnoticeable Backdoor Attacks on Graph Neural Networks](https://mlsanity.com/paper/2303.01263/) (2023)
- [Prototypical Graph Contrastive Learning](https://mlsanity.com/paper/2106.09645/) (2021)
- [MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization](https://mlsanity.com/paper/2210.00102/) (2022)
- [Metropolis-Hastings Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2203.14082/) (2022)
- [ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection](https://mlsanity.com/paper/2312.14535/) (2023)
- [Towards Prototype-Based Self-Explainable Graph Neural Network](https://mlsanity.com/paper/2210.01974/) (2022)
- [Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data](https://mlsanity.com/paper/2202.00097/) (2022)
- [Generative Subgraph Contrast for Self-Supervised Graph Representation Learning](https://mlsanity.com/paper/2207.11996/) (2022)
- [Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment](https://mlsanity.com/paper/2301.02791/) (2023)
- [Disambiguated Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2402.08824/) (2024)
- [Network representation learning: A macro and micro view](https://mlsanity.com/paper/2111.10772/) (2021)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)
- [Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection](https://mlsanity.com/paper/2404.16076/) (2024)
- [RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks](https://mlsanity.com/paper/2108.07481/) (2021)
- [Graph Representation Learning via Aggregation Enhancement](https://mlsanity.com/paper/2201.12843/) (2022)
- [HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption](https://mlsanity.com/paper/2301.12063/) (2023)
- [HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning](https://mlsanity.com/paper/2405.14742/) (2024)

## Abstract (arXiv)

Graph Convolutional Networks (GCNs) have been successfully applied to analyze non-grid data, where the classical convolutional neural networks (CNNs) cannot be directly used. One similarity shared by GCNs and CNNs is the requirement of massive amount of labeled data for network training. In addition, GCNs need the adjacency matrix as input to define the relationship between those non-grid data, which leads to all of data including training, validation and test data typically forms only one graph structures data for training. Furthermore, the adjacency matrix is usually pre-defined and stationary, which makes the data augmentation strategies cannot be employed on the constructed graph structures data to augment the amount of training data. To further improve the learning capacity and model performance under the limited training data, in this paper, we propose two types of self-supervised learning strategies to exploit available information from the input graph structure data itself. Our proposed self-supervised learning strategies are examined on two representative GCN models with three public citation network datasets - Citeseer, Cora and Pubmed. The experimental results demonstrate the generalization ability as well as the portability of our proposed strategies, which can significantly improve the performance of GCNs with the power of self-supervised learning in improving feature learning.