Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Representation learning via Dual-Autoencoder for recommendation.

Fuzhen Zhuang1, Zhiqiang Zhang2, Mingda Qian1

  • 1Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 15, 2017
PubMed
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

Performance of wrist-worn home sleep apnea testing (watch-PAT) among individuals with chronic insomnia: a comparative study with polysomnography.

Frontiers in neurology·2026
Same author

Tailoring the Cu Local Microenvironment to Create Formate Conversion-Desorption Equilibrium for Industrial Level Formaldehyde Electrooxidation.

Angewandte Chemie (International ed. in English)·2026
Same author

Speech as a biomarker for supported diagnosis of major depressive disorder using self-supervised representations.

Nature communications·2026
Same author

MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models With Temporal Distillation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Navigating a fragmented lifeworld: a phenomenological study of schizophrenia among China's Z Generation.

BMC psychiatry·2026
Same author

Case Report: Pulmonary alveolar proteinosis and fibrosis associated with indium-tin-oxide exposure.

Frontiers in medicine·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces Recommendation via Dual-Autoencoder (ReDa), a novel deep learning framework for enhanced recommendation systems. ReDa utilizes autoencoders to learn user and item representations, outperforming traditional matrix factorization methods.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Recommendation systems are crucial for personalized user experiences.
  • Matrix factorization (MF) is a dominant technique but has limitations in utilizing available data.
  • Deep learning offers powerful representation learning capabilities.

Purpose of the Study:

  • To propose a novel deep learning framework for representation learning in recommendation systems.
  • To address the limitations of matrix factorization methods in capturing complex user-item interactions.
  • To improve recommendation performance by learning richer latent representations.

Main Methods:

  • Developed Recommendation via Dual-Autoencoder (ReDa), a deep learning framework.
  • Employed autoencoders for simultaneous learning of user and item representations.
Keywords:
Dual-AutoencoderMatrix factorizationRecommendationRepresentation learning

Related Experiment Videos

  • Utilized a gradient descent method to optimize the learning of hidden representations.

    • Main Results:

    • ReDa effectively learns new hidden representations for users and items.
    • The framework minimizes deviations in training data using learned representations.
    • Extensive experiments show ReDa outperforms state-of-the-art matrix factorization methods on real-world datasets.

    Conclusions:

    • Recommendation via Dual-Autoencoder (ReDa) is an effective deep learning approach for recommendation systems.
    • The proposed method offers a significant improvement over traditional matrix factorization techniques.
    • Autoencoder-based representation learning provides a promising direction for future recommendation research.