ICML 2019oral41 citations

Collective Model Fusion for Multiple Black-Box Experts

Minh Hoang, Nghia Hoang, Bryan Kian Hsiang Low, Carleton Kingsford

Abstract

Model fusion is a fundamental problem in collec-tive machine learning (ML) where independentexperts with heterogeneous learning architecturesare required to combine expertise to improve pre-dictive performance. This is particularly chal-lenging in information-sensitive domains whereexperts do not have access to each other’s internalarchitecture and local data. This paper presentsthe first collective model fusion framework formultiple experts with heterogeneous black-box ar-chitectures. The proposed method will enable thisby addressing the key issues of how black-boxexperts interact to understand the predictive be-haviors of one another; how these understandingscan be represented and shared efficiently amongthemselves; and how the shared understandingscan be combined to generate high-quality consen-sus prediction. The performance of the resultingframework is analyzed theoretically and demon-strated empirically on several datasets.

BibTeX
@InProceedings{pmlr-v97-hoang19a,
  title = 	 {Collective Model Fusion for Multiple Black-Box Experts},
  author =       {Hoang, Minh and Hoang, Nghia and Low, Bryan Kian Hsiang and Kingsford, Carleton},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2742--2750},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/hoang19a/hoang19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/hoang19a.html},
  abstract = 	 {Model fusion is a fundamental problem in collec-tive machine learning (ML) where independentexperts with heterogeneous learning architecturesare required to combine expertise to improve pre-dictive performance. This is particularly chal-lenging in information-sensitive domains whereexperts do not have access to each other’s internalarchitecture and local data. This paper presentsthe first collective model fusion framework formultiple experts with heterogeneous black-box ar-chitectures. The proposed method will enable thisby addressing the key issues of how black-boxexperts interact to understand the predictive be-haviors of one another; how these understandingscan be represented and shared efficiently amongthemselves; and how the shared understandingscan be combined to generate high-quality consen-sus prediction. The performance of the resultingframework is analyzed theoretically and demon-strated empirically on several datasets.}
}
Collective Model Fusion for Multiple Black-Box Experts · ICML 2019