# N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

arXiv: https://arxiv.org/abs/1908.05968 · HTML: https://mlsanity.com/paper/1908.05968/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 30 of 30)

- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks](https://mlsanity.com/paper/2206.08514/) (2022)
- [DeepDPM: Deep Clustering With an Unknown Number of Clusters](https://mlsanity.com/paper/2203.14309/) (2022)
- [Selective Pseudo-label Clustering](https://mlsanity.com/paper/2107.10692/) (2021)
- [Exploring a Principled Framework for Deep Subspace Clustering](https://mlsanity.com/paper/2503.17288/) (2025)
- [Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence](https://mlsanity.com/paper/2407.13933/) (2024)
- [Efficient Deep Clustering of Human Activities and How to Improve Evaluation](https://mlsanity.com/paper/2209.08335/) (2022)
- [Deep Clustering with a Constraint for Topological Invariance based on Symmetric InfoNCE](https://mlsanity.com/paper/2303.03036/) (2023)
- [VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis](https://mlsanity.com/paper/2505.03132/) (2025)
- [Uncertainty in GNN Learning Evaluations: The Importance of a Consistent Benchmark for Community Detection](https://mlsanity.com/paper/2305.06026/) (2023)
- [An Additive Autoencoder for Dimension Estimation](https://mlsanity.com/paper/2210.06773/) (2022)
- [Uncertainty in GNN Learning Evaluations: A Comparison Between Measures for Quantifying Randomness in GNN Community Detection](https://mlsanity.com/paper/2312.09015/) (2023)
- [Forecasting COVID-19 Caseloads Using Unsupervised Embedding Clusters of Social Media Posts](https://mlsanity.com/paper/2205.10408/) (2022)
- [High-dimensional Clustering onto Hamiltonian Cycle](https://mlsanity.com/paper/2304.14531/) (2023)
- [Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary](https://mlsanity.com/paper/2408.06302/) (2024)
- [Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models](https://mlsanity.com/paper/2601.01162/) (2026)
- [MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction](https://mlsanity.com/paper/2511.15179/) (2025)
- [fMBN-E: Efficient Unsupervised Network Structure Ensemble and Selection for Clustering](https://mlsanity.com/paper/2107.02071/) (2021)
- [Unsupervised Behaviour Analysis of News Consumption in Turkish Media](https://mlsanity.com/paper/2202.02056/) (2022)
- [Denoising Cosine Similarity: A Theory-Driven Approach for Efficient Representation Learning](https://mlsanity.com/paper/2304.09552/) (2023)
- [Deep Clustering via Distribution Learning](https://mlsanity.com/paper/2408.03407/) (2024)
- [Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning](https://mlsanity.com/paper/2409.03938/) (2024)
- [Oriented histogram-based vector field embedding for characterizing 4D CT data sets in radiotherapy](https://mlsanity.com/paper/2411.16314/) (2024)
- [Enhanced High-Dimensional Data Visualization through Adaptive Multi-Scale Manifold Embedding](https://mlsanity.com/paper/2503.13954/) (2025)
- [Infinite hierarchical contrastive clustering for personal digital envirotyping](https://mlsanity.com/paper/2505.15022/) (2025)
- [Robust Multi-Manifold Clustering via Simplex Paths](https://mlsanity.com/paper/2507.10710/) (2025)
- [Non-Dissipative Graph Propagation for Non-Local Community Detection](https://mlsanity.com/paper/2508.14097/) (2025)
- [DECOR: Deep Embedding Clustering with Orientation Robustness](https://mlsanity.com/paper/2510.03328/) (2025)
- [SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection](https://mlsanity.com/paper/2511.04692/) (2025)

## Abstract (arXiv)

Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoencoder is typically connected with a clustering network, and the final clustering is jointly learned by both the autoencoder and clustering network. Instead, we propose to learn an autoencoded embedding and then search this further for the underlying manifold. For simplicity, we then cluster this with a shallow clustering algorithm, rather than a deeper network. We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is best able to find the most clusterable manifold in the embedding, suggesting local manifold learning on an autoencoded embedding is effective for discovering higher quality discovering clusters. We quantitatively show across a range of image and time-series datasets that our method has competitive performance against the latest deep clustering algorithms, including out-performing current state-of-the-art on several. We postulate that these results show a promising research direction for deep clustering. The code can be found at https://github.com/rymc/n2d