A Theoretical Framework of the Graph Shift Algorithm

AAAI 2012 pp. 2419-2420

doi:10.1609/AAAI.V26I1.8410 /aaai/2012/fan2012aaai-theoretical/

Abstract

Since no theoretical foundations for proving the convergence of Graph Shift Algorithm have been reported, we provide a generic framework consisting of three key GS components to fit the Zangwill’s convergence theorem. We show that the sequence set generated by the GS procedures always terminates at a local maximum, or at worst, contains a subsequence which converges to a local maximum of the similarity measure function. What is more, a theoretical framework is proposed to apply our proof to a more general case.

PDF AAAI Semantic Scholar

Cite

Text

Fan and Cao. "A Theoretical Framework of the Graph Shift Algorithm." AAAI Conference on Artificial Intelligence, 2012. doi:10.1609/AAAI.V26I1.8410

Markdown

[Fan and Cao. "A Theoretical Framework of the Graph Shift Algorithm." AAAI Conference on Artificial Intelligence, 2012.](https://mlanthology.org/aaai/2012/fan2012aaai-theoretical/) doi:10.1609/AAAI.V26I1.8410

BibTeX

@inproceedings{fan2012aaai-theoretical,
  title     = {{A Theoretical Framework of the Graph Shift Algorithm}},
  author    = {Fan, Xuhui and Cao, Longbing},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2012},
  pages     = {2419-2420},
  doi       = {10.1609/AAAI.V26I1.8410},
  url       = {https://mlanthology.org/aaai/2012/fan2012aaai-theoretical/}
}