# Unsupervised Continual Learning in Streaming Environments

arXiv: https://arxiv.org/abs/2109.09282 · HTML: https://mlsanity.com/paper/2109.09282/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 21 of 21)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Continuous Learning in Single-Incremental-Task Scenarios](https://mlsanity.com/paper/1806.08568/) (2018)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [t-SNE-CUDA: GPU-Accelerated t-SNE and its Applications to Modern Data](https://mlsanity.com/paper/1807.11824/) (2018)
- [Continual Learning Using Bayesian Neural Networks](https://mlsanity.com/paper/1910.04112/) (2019)
- [DEVDAN: Deep Evolving Denoising Autoencoder](https://mlsanity.com/paper/1910.04062/) (2019)
- [Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments](https://mlsanity.com/paper/1810.07348/) (2018)
- [Automatic Construction of Multi-layer Perceptron Network from Streaming Examples](https://mlsanity.com/paper/1910.03437/) (2019)
- [Dual Adversarial Auto-Encoders for Clustering](https://mlsanity.com/paper/2008.10038/) (2020)
- [Online Tool Condition Monitoring Based on Parsimonious Ensemble+](https://mlsanity.com/paper/1711.01843/) (2017)
- [Weakly Supervised Deep Learning Approach in Streaming Environments](https://mlsanity.com/paper/1911.00847/) (2019)
- [PALM: An Incremental Construction of Hyperplanes for Data Stream Regression](https://mlsanity.com/paper/1805.04258/) (2018)
- [MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings](https://mlsanity.com/paper/2007.09502/) (2020)

## Built on by (most cited first, 19 of 19)

- [Reinforced Continual Learning for Graphs](https://mlsanity.com/paper/2209.01556/) (2022)
- [Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects](https://mlsanity.com/paper/2312.17004/) (2023)
- [Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning](https://mlsanity.com/paper/2308.02346/) (2023)
- [Assessor-Guided Learning for Continual Environments](https://mlsanity.com/paper/2303.11624/) (2023)
- [Scalable Adversarial Online Continual Learning](https://mlsanity.com/paper/2209.01558/) (2022)
- [Few-Shot Continual Learning via Flat-to-Wide Approaches](https://mlsanity.com/paper/2306.14369/) (2023)
- [Few-Shot Class Incremental Learning via Robust Transformer Approach](https://mlsanity.com/paper/2405.05984/) (2024)
- [Autonomous Cross Domain Adaptation under Extreme Label Scarcity](https://mlsanity.com/paper/2209.01548/) (2022)
- [Continual Knowledge Consolidation LORA for Domain Incremental Learning](https://mlsanity.com/paper/2510.16077/) (2025)
- [Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection](https://mlsanity.com/paper/2603.06757/) (2026)
- [Cross-Domain Continual Learning via CLAMP](https://mlsanity.com/paper/2405.07142/) (2024)
- [Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2406.18574/) (2024)
- [Evolving Restricted Boltzmann Machine-Kohonen Network for Online Clustering](https://mlsanity.com/paper/2402.09167/) (2024)
- [From Lab to Pocket: A Novel Continual Learning-based Mobile Application for Screening COVID-19](https://mlsanity.com/paper/2410.12589/) (2024)
- [CND-IDS: Continual Novelty Detection for Intrusion Detection Systems](https://mlsanity.com/paper/2502.14094/) (2025)
- [Class Incremental Continual Learning with Self-Organizing Maps and Synthetic Replay](https://mlsanity.com/paper/2508.21240/) (2025)
- [Source-Free Cross-Domain Continual Learning](https://mlsanity.com/paper/2510.01649/) (2025)
- [Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation](https://mlsanity.com/paper/2606.07474/) (2026)
- [Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation](https://mlsanity.com/paper/2606.30190/) (2026)

## Abstract (arXiv)

A deep clustering network is desired for data streams because of its aptitude in extracting natural features thus bypassing the laborious feature engineering step. While automatic construction of the deep networks in streaming environments remains an open issue, it is also hindered by the expensive labeling cost of data streams rendering the increasing demand for unsupervised approaches. This paper presents an unsupervised approach of deep clustering network construction on the fly via simultaneous deep learning and clustering termed Autonomous Deep Clustering Network (ADCN). It combines the feature extraction layer and autonomous fully connected layer in which both network width and depth are self-evolved from data streams based on the bias-variance decomposition of reconstruction loss. The self-clustering mechanism is performed in the deep embedding space of every fully connected layer while the final output is inferred via the summation of cluster prediction score. Further, a latent-based regularization is incorporated to resolve the catastrophic forgetting issue. A rigorous numerical study has shown that ADCN produces better performance compared to its counterparts while offering fully autonomous construction of ADCN structure in streaming environments with the absence of any labeled samples for model updates. To support the reproducible research initiative, codes, supplementary material, and raw results of ADCN are made available in urlhttps://tinyurl.com/AutonomousDCN.