Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction

@article{Wang2014GeneralizedAA,
  title={Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction},
  author={Wei Wang and Y. Huang and Yizhou Wang and Liang Wang},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year={2014},
  pages={496-503}
}
  • Wei Wang, Y. Huang, +1 author Liang Wang
  • Published 2014
  • Mathematics, Computer Science
  • 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops
  • The autoencoder algorithm and its deep version as traditional dimensionality reduction methods have achieved great success via the powerful representability of neural networks. However, they just use each instance to reconstruct itself and ignore to explicitly model the data relation so as to discover the underlying effective manifold structure. In this paper, we propose a dimensionality reduction method by manifold learning, which iteratively explores data relation and use the relation to… CONTINUE READING
    150 Citations

    Figures, Tables, and Topics from this paper

    Relation-Guided Representation Learning
    • 3
    • PDF
    Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
    • 4
    • PDF
    Solving Forward and Inverse Problems Using Autoencoders
    • 1
    Auto-encoder based dimensionality reduction
    • 171
    Nonparametrically Guided Autoencoder with Laplace Approximation for dimensionality reduction
    • 5
    Graph Regularized Restricted Boltzmann Machine
    • 31
    • PDF
    Reconstructible Nonlinear Dimensionality Reduction via Joint Dictionary Learning
    • 16
    Unsupervised Multi-Manifold Clustering by Learning Deep Representation
    • 33
    • PDF
    Dimensionality reduction strategy based on auto-encoder
    • 12
    Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation
    • 18
    • PDF

    References

    SHOWING 1-10 OF 24 REFERENCES
    Contractive Auto-Encoders: Explicit Invariance During Feature Extraction
    • 1,065
    • PDF
    Extracting and composing robust features with denoising autoencoders
    • 4,291
    • PDF
    Learning Algorithms for the Classification Restricted Boltzmann Machine
    • 230
    • PDF
    Locality Preserving Projections
    • 3,847
    • Highly Influential
    • PDF
    Graph Embedding and Extensions: A General Framework for Dimensionality Reduction
    • 1,764
    • Highly Influential
    • PDF
    Reducing the Dimensionality of Data with Neural Networks
    • 11,882
    • Highly Influential
    • PDF
    Neighborhood preserving embedding
    • X. He, Deng Cai, S. Yan, H. Zhang
    • Computer Science, Mathematics
    • Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
    • 2005
    • 1,391
    • PDF
    Sparse deep belief net model for visual area V2
    • 975
    • PDF
    Generalized principal component analysis (GPCA)
    • R. Vidal, Y. Ma, S. Sastry
    • Mathematics, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2005
    • 957
    • PDF