Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Sep 25, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

RCA: A Deep Collaborative Autoencoder Approach for Anomaly Detection.

Boyang Liu¹, Ding Wang¹, Kaixiang Lin¹

¹Michigan State University, Department of Computer Science and Engineering.

IJCAI : Proceedings of the Conference

|April 28, 2022

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Epithelial and Interstitial Gli2 Activation Correlates With Renal Tubulointerstitial Fibrosis and Facilitates FoxM1-Associated Myofibroblast Phenotypic Transition.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026

Same author

Electronic and steric effects of phosphine ligands on the linear regioselectivity of propylene methoxycarbonylation.

Communications chemistry·2026

Same author

Unsupervised Anomaly Detection in Medical Imaging: A Survey of Methods, Challenges, and Future Directions.

Bioengineering (Basel, Switzerland)·2026

Same author

Impact of Mono-, Di-, and Trivalent Ions on the Rheology of Borate-Crosslinked Guar Fracturing Fluids.

Gels (Basel, Switzerland)·2026

Same author

Pangenome and resequencing analyses reveal flowering evolution and genetic control in Cerasus.

Nature communications·2026

Same author

Slow-wave sleep engages brainstem circuitry to prevent stress-induced anxiety.

Neuron·2026

Same journal

Recent Advances in Predictive Modeling with Electronic Health Records.

IJCAI : proceedings of the conference·2025

Same journal

ReBandit: Random Effects Based Online RL Algorithm for Reducing Cannabis Use.

IJCAI : proceedings of the conference·2024

Same journal

Predictive Modeling with Temporal Graphical Representation on Electronic Health Records.

IJCAI : proceedings of the conference·2024

Same journal

Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning.

IJCAI : proceedings of the conference·2023

Same journal

Stabilizing and Enhancing Link Prediction through Deepened Graph Auto-Encoders.

IJCAI : proceedings of the conference·2022

Same journal

What Does the Evidence Say? Models to Help Make Sense of the Biomedical Literature.

IJCAI : proceedings of the conference·2021

See all related articles

This study introduces a robust framework using collaborative autoencoders for unsupervised anomaly detection (AD). The method effectively identifies normal data points and their representations, outperforming deep neural network approaches and showing resilience to missing values.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Unsupervised anomaly detection (AD) is critical for various applications.
Deep neural networks (DNNs), particularly autoencoders, are increasingly used for AD.
A key challenge is that anomalies can have small reconstruction errors in DNNs, limiting effectiveness.

Purpose of the Study:

To propose a robust framework for unsupervised anomaly detection using collaborative autoencoders.
To jointly identify normal observations and learn their feature representations.
To address the limitation of small anomaly reconstruction errors in DNN-based AD.

Main Methods:

Developed a novel framework employing collaborative autoencoders.
The framework learns feature representations for normal data.

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Sep 25, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

It simultaneously identifies normal observations within the dataset.

Main Results:

The proposed framework demonstrates outstanding performance compared to existing DNN-based AD methods.
Empirical results highlight the framework's robustness to missing values.
Theoretical properties of the framework were investigated and validated.

Conclusions:

The collaborative autoencoder framework offers a more effective approach to unsupervised anomaly detection.
This method overcomes limitations of standard autoencoders in handling complex, over-parameterized DNNs.
The framework shows significant promise for real-world applications, especially with incomplete data.