# A Noise-Resilient Semi-Supervised Graph Autoencoder for Overlapping Semantic Community Detection

arXiv: https://arxiv.org/abs/2505.05965 · HTML: https://mlsanity.com/paper/2505.05965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 8 of 8)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [A Comprehensive Survey on Community Detection with Deep Learning](https://mlsanity.com/paper/2105.12584/) (2021)
- [A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2101.01669/) (2021)
- [Overlapping Community Detection with Graph Neural Networks](https://mlsanity.com/paper/1909.12201/) (2019)
- [Community Detection in Networks with Node Attributes](https://mlsanity.com/paper/1401.7267/) (2014)
- [CommunityGAN: Community Detection with Generative Adversarial Nets](https://mlsanity.com/paper/1901.06631/) (2019)
- [Dual-channel Heterophilic Message Passing for Graph Fraud Detection](https://mlsanity.com/paper/2504.14205/) (2025)

## Abstract (arXiv)

Community detection in networks with overlapping structures remains a significant challenge, particularly in noisy real-world environments where integrating topology, node attributes, and prior information is critical. To address this, we propose a semi-supervised graph autoencoder that combines graph multi-head attention and modularity maximization to robustly detect overlapping communities. The model learns semantic representations by fusing structural, attribute, and prior knowledge while explicitly addressing noise in node features. Key innovations include a noise-resistant architecture and a semantic semi-supervised design optimized for community quality through modularity constraints. Experiments demonstrate superior performance the model outperforms state-of-the-art methods in overlapping community detection (improvements in NMI and F1-score) and exhibits exceptional robustness to attribute noise, maintaining stable performance under 60% feature corruption. These results highlight the importance of integrating attribute semantics and structural patterns for accurate community discovery in complex networks.