# Deep Attention-guided Graph Clustering with Dual Self-supervision

arXiv: https://arxiv.org/abs/2111.05548 · HTML: https://mlsanity.com/paper/2111.05548/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 79 references that are in the map.
- First posted on arXiv 10 Nov 2021.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Combining Label Propagation and Simple Models Out-performs Graph Neural Networks](https://mlsanity.com/paper/2010.13993/) (2020)
- [Graph Embedding Techniques, Applications, and Performance: A Survey](https://mlsanity.com/paper/1705.02801/) (2017)
- [Attributed Graph Clustering: A Deep Attentional Embedding Approach](https://mlsanity.com/paper/1906.06532/) (2019)
- [Structural Deep Clustering Network](https://mlsanity.com/paper/2002.01633/) (2020)
- [A Survey on Network Embedding](https://mlsanity.com/paper/1711.08752/) (2017)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)
- [Graph Embedded Pose Clustering for Anomaly Detection](https://mlsanity.com/paper/1912.11850/) (2019)
- [Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning](https://mlsanity.com/paper/1908.02441/) (2019)
- [Learning Graph Embedding with Adversarial Training Methods](https://mlsanity.com/paper/1901.01250/) (2019)
- [Deep Fusion Clustering Network](https://mlsanity.com/paper/2012.09600/) (2020)
- [Attention-driven Graph Clustering Network](https://mlsanity.com/paper/2108.05499/) (2021)
- [Deep clustering: On the link between discriminative models and K-means](https://mlsanity.com/paper/1810.04246/) (2018)
- [Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation](https://mlsanity.com/paper/2004.14705/) (2020)
- [Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking](https://mlsanity.com/paper/2103.16086/) (2021)
- [CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data](https://mlsanity.com/paper/1705.07091/) (2017)
- [Consistent Multiple Graph Embedding for Multi-View Clustering](https://mlsanity.com/paper/2105.04880/) (2021)
- [Maximum Entropy Subspace Clustering Network](https://mlsanity.com/paper/2012.03176/) (2020)
- [Decorrelated Clustering with Data Selection Bias](https://mlsanity.com/paper/2006.15874/) (2020)
- [Clustering Ensemble Meets Low-rank Tensor Approximation](https://mlsanity.com/paper/2012.08916/) (2020)

## Built on by (most cited first, 10 of 10)

- [A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource](https://mlsanity.com/paper/2211.12875/) (2022)
- [Improved Dual Correlation Reduction Network](https://mlsanity.com/paper/2202.12533/) (2022)
- [A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning](https://mlsanity.com/paper/2505.16341/) (2025)
- [EGRC-Net: Embedding-induced Graph Refinement Clustering Network](https://mlsanity.com/paper/2211.10627/) (2022)
- [Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images](https://mlsanity.com/paper/2403.01799/) (2024)
- [You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering](https://mlsanity.com/paper/2511.21193/) (2025)
- [Discriminative Anchor Learning for Efficient Multi-view Clustering](https://mlsanity.com/paper/2409.16904/) (2024)
- [Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering](https://mlsanity.com/paper/2506.09920/) (2025)
- [Stochastic Deep Graph Clustering for Practical Group Formation](https://mlsanity.com/paper/2511.02879/) (2025)
- [Weighted Graph Clustering via Scale Contraction and Graph Structure Learning](https://mlsanity.com/paper/2601.17307/) (2026)

## Abstract (arXiv)

Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance limitation. To this end, we propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC). Specifically, DAGC first utilizes a heterogeneity-wise fusion module to adaptively integrate the features of an auto-encoder and a graph convolutional network in each layer and then uses a scale-wise fusion module to dynamically concatenate the multi-scale features in different layers. Such modules are capable of learning a discriminative feature embedding via an attention-based mechanism. In addition, we design a distribution-wise fusion module that leverages cluster assignments to acquire clustering results directly. To better explore the discriminative information from the cluster assignments, we develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Extensive experiments validate that our method consistently outperforms state-of-the-art methods on six benchmark datasets. Especially, our method improves the ARI by more than 18.14% over the best baseline.