An Introductory Survey to Autoencoder-based Deep Clustering -- Sandboxes for Combining Clustering with Deep Learning

2025-04-02

AI Summary

To address the curse of dimensionality and insufficient representation learning in high-dimensional clustering, this paper systematically surveys and restructures autoencoder-based deep clustering methods. We propose a “sandbox-style” unified framework that emphasizes the domain-agnostic nature and task-customizability of autoencoders, jointly optimizing reconstruction learning with clustering objectives—such as k-means coupling or co-designed objective functions—to achieve consistent learning of low-dimensional nonlinear representations and intrinsic cluster structure. Through comparative analysis of over a dozen state-of-the-art algorithms, we clarify their design motivations, modeling assumptions, and applicability boundaries, establishing the first structured methodology for deep clustering. This work provides a scalable paradigm foundation and practical benchmark, significantly improving clustering accuracy, robustness, and interpretability.

Technology Category

• Machine Learning: Clustering
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Autoencoders offer a general way of learning low-dimensional, non-linear representations from data without labels. This is achieved without making any particular assumptions about the data type or other domain knowledge. The generality and domain agnosticism in combination with their simplicity make autoencoders a perfect sandbox for researching and developing novel (deep) clustering algorithms. Clustering methods group data based on similarity, a task that benefits from the lower-dimensional representation learned by an autoencoder, mitigating the curse of dimensionality. Specifically, the combination of deep learning with clustering, called Deep Clustering, enables to learn a representation tailored to specific clustering tasks, leading to high-quality results. This survey provides an introduction to fundamental autoencoder-based deep clustering algorithms that serve as building blocks for many modern approaches.

Problem

• Autoencoders learn low-dimensional representations without labels
• Deep clustering combines autoencoders with similarity-based grouping
• Survey introduces autoencoder-based deep clustering foundational algorithms

Innovation

• Autoencoders learn low-dimensional representations
• Combine deep learning with clustering tasks
• Mitigate dimensionality curse via representation