Skip to yearly menu bar Skip to main content


Poster

Collective Model Fusion for Multiple Black-Box Experts

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

Pacific Ballroom #184

Keywords: [ Approximate Inference ] [ Parallel and Distributed Learning ]


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.

Live content is unavailable. Log in and register to view live content