# Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream

arXiv: https://arxiv.org/abs/2206.04792 · HTML: https://mlsanity.com/paper/2206.04792/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [Deep Structured Energy Based Models for Anomaly Detection](https://mlsanity.com/paper/1605.07717/) (2016)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [Challenges in Benchmarking Stream Learning Algorithms with Real-world Data](https://mlsanity.com/paper/2005.00113/) (2020)
- [Robust Subspace Recovery Layer for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.00152/) (2019)
- [MSTREAM: Fast Anomaly Detection in Multi-Aspect Streams](https://mlsanity.com/paper/2009.08451/) (2020)

## Built on by (most cited first, 13 of 13)

- [Online Boosting Adaptive Learning under Concept Drift for Multistream Classification](https://mlsanity.com/paper/2312.10841/) (2023)
- [Online Drift Detection with Maximum Concept Discrepancy](https://mlsanity.com/paper/2407.05375/) (2024)
- [METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection](https://mlsanity.com/paper/2312.16831/) (2023)
- [PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream](https://mlsanity.com/paper/2302.05550/) (2023)
- [Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding](https://mlsanity.com/paper/2304.04099/) (2023)
- [SCStory: Self-supervised and Continual Online Story Discovery](https://mlsanity.com/paper/2312.03725/) (2023)
- [One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms](https://mlsanity.com/paper/2306.01507/) (2023)
- [Multi-Aspect Mining and Anomaly Detection for Heterogeneous Tensor Streams](https://mlsanity.com/paper/2602.04917/) (2026)
- [iADCPS: Time Series Anomaly Detection for Evolving Cyber-physical Systems via Incremental Meta-learning](https://mlsanity.com/paper/2504.04374/) (2025)
- [A Graph-based Framework for Online Time Series Anomaly Detection Using Model Ensemble](https://mlsanity.com/paper/2601.01403/) (2026)
- [Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams](https://mlsanity.com/paper/2602.09681/) (2026)
- [Drift-Aware Variational Autoencoder-based Anomaly Detection with Two-level Ensembling](https://mlsanity.com/paper/2602.12976/) (2026)
- [Catching Every Ripple: Enhanced Anomaly Awareness via Dynamic Concept Adaptation](https://mlsanity.com/paper/2604.14726/) (2026)

## Abstract (arXiv)

Online anomaly detection from a data stream is critical for the safety and security of many applications but is facing severe challenges due to complex and evolving data streams from IoT devices and cloud-based infrastructures. Unfortunately, existing approaches fall too short for these challenges; online anomaly detection methods bear the burden of handling the complexity while offline deep anomaly detection methods suffer from the evolving data distribution. This paper presents a framework for online deep anomaly detection, ARCUS, which can be instantiated with any autoencoder-based deep anomaly detection methods. It handles the complex and evolving data streams using an adaptive model pooling approach with two novel techniques: concept-driven inference and drift-aware model pool update; the former detects anomalies with a combination of models most appropriate for the complexity, and the latter adapts the model pool dynamically to fit the evolving data streams. In comprehensive experiments with ten data sets which are both high-dimensional and concept-drifted, ARCUS improved the anomaly detection accuracy of the streaming variants of state-of-the-art autoencoder-based methods and that of the state-of-the-art streaming anomaly detection methods by up to 22% and 37%, respectively.