Deep Clustering: Papers and Resources
May 12, 2026 ยท View on GitHub
Deep Clustering: Papers and Resources
This repository is a curated reading list for deep clustering and closely related clustering methods. It is designed as a lightweight entry point for researchers who want a broad view of the area, representative papers, and public codebases when available.
Highlights
- [2024.08] Our survey paper, A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions, has been accepted by ACM Computing Surveys.
- [2022.06] We released a new survey paper based on this repository and would be happy to hear any feedback or discussion.
Scope
This repository intentionally has a relatively broad scope. In addition to canonical deep clustering papers, it may also include related work on multi-view clustering, graph clustering, subspace clustering, fairness, optimal transport, and application-driven clustering when they are useful to the deep clustering community.
Contents
- Survey Papers
- General Deep Clustering
- Multi-view Clustering
- Special Settings
- Data-specific and Application-specific Clustering
Survey Papers
| Survey Paper | Conference |
|---|---|
| :triangular_flag_on_post: A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions | ACM Computing Surveys |
| Deep Clustering: A Comprehensive Survey | IEEE TNNLS 2024 |
| A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture | IEEE ACCESS 2018 |
| Clustering with Deep Learning: Taxonomy and New Methods | arXiv 2018 |
| Unsupervised clustering for deep learning: A tutorial survey | APH 2018 |
General Deep Clustering
Core and Related Methods
Autoencoder and Generative Methods
Contrastive and Self-Supervised Methods
Subspace and Spectral Methods
Multi-view Clustering
Complete Multi-view Clustering
Incomplete, Unpaired, and Federated Multi-view Clustering
Special Settings
Data-specific and Application-specific Clustering
Graph Clustering
A dedicated graph-focused collection is also maintained in Deep Graph Clustering.
Image and Visual Recognition
Text and Intent Discovery
| Paper | Method | Conference | Code |
|---|---|---|---|
| DUIC: User-descriptive intention guided clustering for personalized and understandable document partitions | DUIC | Information Processing & Management 2026 | - |
| A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery | USNID | IEEE TKDE 2023 | Pytorch |
| Deep Clustering of Text Representations for Supervision-Free Probing of Syntax | SyntDEC | AAAI 2022 | - |
| A hybrid approach for text document clustering using Jaya optimization algorithm | HJO-DC | ESWA 2021 | - |
| Discovering New Intents with Deep Aligned Clustering | DeepAligned | AAAI 2021 | Pytorch |
| A text document clustering method based on weighted Bert model | - | ITNEC 2020 | - |
| Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement | CDAC+ | AAAI 2020 | Pytorch |
| Learning to cluster documents into workspaces using large scale activity logs | - | SIGKDD 2020 | - |
| Text document clustering using spectral clustering algorithm with particle swarm optimization | SCPSO | ESWA 2019 | Python |
Time Series and Video
Bioinformatics and Single-cell Data
| Paper | Method | Conference | Code |
|---|---|---|---|
| A Deep Variational Approach to Clustering Survival Data | VaDeSC | ICLR 2022 | TensorFlow |
| Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis | ItClust | Nature machine intelligence 2020 | Keras |
| Clustering single-cell RNA-seq data with a model-based deep learning approach | scDeepCluster | Nature Machine Intelligence 2019 | Keras |
Other Applications
| Paper | Method | Conference | Code |
|---|---|---|---|
| Sign prediction in sparse social networks using clustering and collaborative filtering | - | TJSC 2022 | - |
| CCCF: Improving collaborative filtering via scalable user-item co-clustering | CCCF | WSDM 2016 | - |
Contributing
Suggestions, corrections, and pull requests are welcome, especially for:
- missing influential papers
- broken or outdated code links
- duplicate entries
- better sub-topic organization
Tips
If you find this repository useful to your research or work, please consider starring it.