SpectralNet: Spectral Clustering using Deep Neural Networks

@article{Shaham2018SpectralNetSC,
  title={SpectralNet: Spectral Clustering using Deep Neural Networks},
  author={Uri Shaham and Kelly P. Stanton and Henry Li and Boaz Nadler and Ronen Basri and Yuval Kluger},
  journal={ArXiv},
  year={2018},
  volume={abs/1801.01587}
}
Spectral clustering is a leading and popular technique in unsupervised data analysis. Two of its major limitations are scalability and generalization of the spectral embedding (i.e., out-of-sample-extension). In this paper we introduce a deep learning approach to spectral clustering that overcomes the above shortcomings. Our network, which we call SpectralNet, learns a map that embeds input data points into the eigenspace of their associated graph Laplacian matrix and subsequently clusters them… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 30 CITATIONS

Diffusion Variational Autoencoders

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Variational Random Walk Autoencoders.

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

An Automatic Clustering Algorithm Based on Region Segmentation

VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Multilayer Network Data Clustering

VIEW 12 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

OrthoNet: Multilayer Network Data Clustering

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Scalable Laplacian K-modes

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Big-Data Clustering: K-Means or K-Indicators?

Feiyu Chen, Yuchen Yang, Xu Liwei, Taiping Zhang, Yin Zhang
  • ArXiv
  • 2019
VIEW 1 EXCERPT
CITES METHODS

Clustering With Orthogonal AutoEncoder

  • IEEE Access
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Joint Unsupervised Learning of Deep Representations and Image Clusters

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Normalized Cuts and Image Segmentation

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2000
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…