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={CoRR},
  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
Recent Discussions
This paper has been referenced on Twitter 43 times over the past 90 days. VIEW TWEETS

References

Publications referenced by this paper.
Showing 1-10 of 25 references

Similar Papers

Loading similar papers…