# AutoEmbedder: A semi-supervised DNN embedding system for clustering

arXiv: https://arxiv.org/abs/2007.05830 · HTML: https://mlsanity.com/paper/2007.05830/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Label-Efficient Learning in Agriculture: A Comprehensive Review](https://mlsanity.com/paper/2305.14691/) (2023)
- [Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodings](https://mlsanity.com/paper/2210.14056/) (2022)
- [U-vectors: Generating clusterable speaker embedding from unlabeled data](https://mlsanity.com/paper/2102.03868/) (2021)
- [Angular Constraint Embedding via SpherePair Loss for Constrained Clustering](https://mlsanity.com/paper/2510.06907/) (2025)
- [Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification](https://mlsanity.com/paper/2404.17173/) (2024)
- [A Novel Method for News Article Event-Based Embedding](https://mlsanity.com/paper/2405.13071/) (2024)
- [Clustering-Guided Multi-Layer Contrastive Representation Learning for Citrus Disease Classification](https://mlsanity.com/paper/2507.11171/) (2025)
- [Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision](https://mlsanity.com/paper/2608.12027/) (2026)

## Abstract (arXiv)

Clustering is widely used in unsupervised learning method that deals with unlabeled data. Deep clustering has become a popular study area that relates clustering with Deep Neural Network (DNN) architecture. Deep clustering method downsamples high dimensional data, which may also relate clustering loss. Deep clustering is also introduced in semi-supervised learning (SSL). Most SSL methods depend on pairwise constraint information, which is a matrix containing knowledge if data pairs can be in the same cluster or not. This paper introduces a novel embedding system named AutoEmbedder, that downsamples higher dimensional data to clusterable embedding points. To the best of our knowledge, this is the first research endeavor that relates to traditional classifier DNN architecture with a pairwise loss reduction technique. The training process is semi-supervised and uses Siamese network architecture to compute pairwise constraint loss in the feature learning phase. The AutoEmbedder outperforms most of the existing DNN based semi-supervised methods tested on famous datasets.