# VGAER: Graph Neural Network Reconstruction based Community Detection

arXiv: https://arxiv.org/abs/2201.04066 · HTML: https://mlsanity.com/paper/2201.04066/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 8 Jan 2022.

## Builds on (most cited first, 13 of 13)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Structural Deep Clustering Network](https://mlsanity.com/paper/2002.01633/) (2020)
- [Attributed Graph Clustering via Adaptive Graph Convolution](https://mlsanity.com/paper/1906.01210/) (2019)
- [Adaptive Graph Encoder for Attributed Graph Embedding](https://mlsanity.com/paper/2007.01594/) (2020)
- [GEMSEC: Graph Embedding with Self Clustering](https://mlsanity.com/paper/1802.03997/) (2018)
- [Overlapping Community Detection with Graph Neural Networks](https://mlsanity.com/paper/1909.12201/) (2019)
- [Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective](https://mlsanity.com/paper/2107.01475/) (2021)
- [Supervised Community Detection with Line Graph Neural Networks](https://mlsanity.com/paper/1705.08415/) (2017)
- [Unsupervised Constrained Community Detection via Self-Expressive Graph Neural Network](https://mlsanity.com/paper/2011.14078/) (2020)

## Built on by (most cited first, 14 of 14)

- [Over-Squashing in Graph Neural Networks: A Comprehensive survey](https://mlsanity.com/paper/2308.15568/) (2023)
- [GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis](https://mlsanity.com/paper/2203.09034/) (2022)
- [Uncertainty in GNN Learning Evaluations: The Importance of a Consistent Benchmark for Community Detection](https://mlsanity.com/paper/2305.06026/) (2023)
- [Contrastive Deep Nonnegative Matrix Factorization for Community Detection](https://mlsanity.com/paper/2311.02357/) (2023)
- [Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks](https://mlsanity.com/paper/2312.16418/) (2023)
- [Uncertainty in GNN Learning Evaluations: A Comparison Between Measures for Quantifying Randomness in GNN Community Detection](https://mlsanity.com/paper/2312.09015/) (2023)
- [CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learning](https://mlsanity.com/paper/2311.11073/) (2023)
- [Migrate Demographic Group For Fair GNNs](https://mlsanity.com/paper/2306.04212/) (2023)
- [Unsupervised Optimisation of GNNs for Node Clustering](https://mlsanity.com/paper/2402.07845/) (2024)
- [Non-Dissipative Graph Propagation for Non-Local Community Detection](https://mlsanity.com/paper/2508.14097/) (2025)
- [FTSCommDetector: Discovering Behavioral Communities through Temporal Synchronization](https://mlsanity.com/paper/2510.00014/) (2025)
- [Weighted Graph Clustering via Scale Contraction and Graph Structure Learning](https://mlsanity.com/paper/2601.17307/) (2026)
- [Robust Contrastive Graph Clustering with Adaptive Local-Global Integration](https://mlsanity.com/paper/2605.28209/) (2026)
- [ModTGCN: Modularity-aware Graph Neural Networks for Text Classification](https://mlsanity.com/paper/2606.23694/) (2026)

## Abstract (arXiv)

Community detection is a fundamental and important issue in network science, but there are only a few community detection algorithms based on graph neural networks, among which unsupervised algorithms are almost blank. By fusing the high-order modularity information with network features, this paper proposes a Variational Graph AutoEncoder Reconstruction based community detection VGAER for the first time, and gives its non-probabilistic version. They do not need any prior information. We have carefully designed corresponding input features, decoder, and downstream tasks based on the community detection task and these designs are concise, natural, and perform well (NMI values under our design are improved by 59.1% - 565.9%). Based on a series of experiments with wide range of datasets and advanced methods, VGAER has achieved superior performance and shows strong competitiveness and potential with a simpler design. Finally, we report the results of algorithm convergence analysis and t-SNE visualization, which clearly depicted the stable performance and powerful network modularity ability of VGAER. Our codes are available at https://github.com/qcydm/VGAER.