# Unsupervised Graph Clustering with Deep Structural Entropy

arXiv: https://arxiv.org/abs/2505.14040 · HTML: https://mlsanity.com/paper/2505.14040/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 20 May 2025.

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

- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification](https://mlsanity.com/paper/2306.08385/) (2023)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Towards Unsupervised Deep Graph Structure Learning](https://mlsanity.com/paper/2201.06367/) (2022)
- [SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks](https://mlsanity.com/paper/2102.05034/) (2021)
- [Structural Entropy Guided Graph Hierarchical Pooling](https://mlsanity.com/paper/2206.13510/) (2022)
- [Graph-Revised Convolutional Network](https://mlsanity.com/paper/1911.07123/) (2019)
- [HARP: Hierarchical Representation Learning for Networks](https://mlsanity.com/paper/1706.07845/) (2017)
- [Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering](https://mlsanity.com/paper/2107.08562/) (2021)
- [SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization](https://mlsanity.com/paper/2303.09778/) (2023)
- [Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling](https://mlsanity.com/paper/1910.11436/) (2019)
- [CONVERT:Contrastive Graph Clustering with Reliable Augmentation](https://mlsanity.com/paper/2308.08963/) (2023)
- [LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering](https://mlsanity.com/paper/2405.11801/) (2024)
- [Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning](https://mlsanity.com/paper/2202.08480/) (2022)
- [Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning](https://mlsanity.com/paper/2305.18962/) (2023)
- [Unsupervised Social Bot Detection via Structural Information Theory](https://mlsanity.com/paper/2404.13595/) (2024)
- [Structured Graph Learning for Clustering and Semi-supervised Classification](https://mlsanity.com/paper/2008.13429/) (2020)
- [SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detection](https://mlsanity.com/paper/2405.11225/) (2024)
- [Spiking Graph Neural Network on Riemannian Manifolds](https://mlsanity.com/paper/2410.17941/) (2024)
- [Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection](https://mlsanity.com/paper/2312.11891/) (2023)
- [Hierarchical State Abstraction Based on Structural Information Principles](https://mlsanity.com/paper/2304.12000/) (2023)
- [MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization](https://mlsanity.com/paper/2311.02880/) (2023)
- [Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphs](https://mlsanity.com/paper/2309.01899/) (2023)
- [SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning](https://mlsanity.com/paper/2305.04501/) (2023)
- [USER: Unsupervised Structural Entropy-based Robust Graph Neural Network](https://mlsanity.com/paper/2302.05889/) (2023)

## Built on by (most cited first, 4 of 4)

- [KAT-Coder-V2.5 Technical Report](https://mlsanity.com/paper/2607.05471/) (2026)
- [Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering](https://mlsanity.com/paper/2603.20829/) (2026)
- [Bridge the Gaps: Heterogeneous Attributed Graph Clustering via Quaternion Representation Learning](https://mlsanity.com/paper/2606.23199/) (2026)
- [Selective Hypergraph Refinement for Frozen Graph Clustering](https://mlsanity.com/paper/2609.03265/) (2026)

## Abstract (arXiv)

Research on Graph Structure Learning (GSL) provides key insights for graph-based clustering, yet current methods like Graph Neural Networks (GNNs), Graph Attention Networks (GATs), and contrastive learning often rely heavily on the original graph structure. Their performance deteriorates when the original graph's adjacency matrix is too sparse or contains noisy edges unrelated to clustering. Moreover, these methods depend on learning node embeddings and using traditional techniques like k-means to form clusters, which may not fully capture the underlying graph structure between nodes. To address these limitations, this paper introduces DeSE, a novel unsupervised graph clustering framework incorporating Deep Structural Entropy. It enhances the original graph with quantified structural information and deep neural networks to form clusters. Specifically, we first propose a method for calculating structural entropy with soft assignment, which quantifies structure in a differentiable form. Next, we design a Structural Learning layer (SLL) to generate an attributed graph from the original feature data, serving as a target to enhance and optimize the original structural graph, thereby mitigating the issue of sparse connections between graph nodes. Finally, our clustering assignment method (ASS), based on GNNs, learns node embeddings and a soft assignment matrix to cluster on the enhanced graph. The ASS layer can be stacked to meet downstream task requirements, minimizing structural entropy for stable clustering and maximizing node consistency with edge-based cross-entropy loss. Extensive comparative experiments are conducted on four benchmark datasets against eight representative unsupervised graph clustering baselines, demonstrating the superiority of the DeSE in both effectiveness and interpretability.