ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
This work addresses privacy constraints in distributed ML for clients with centralized expert models, but it is incremental as it builds on an existing framework.
The paper tackles the problem of matching client-side model components with server-side components in Split Learning without sharing raw data, proposing an extension to ExpertMatcher that uses hidden representations to automate this process.
Recently, there has been the development of Split Learning, a framework for distributed computation where model components are split between the client and server (Vepakomma et al., 2018b). As Split Learning scales to include many different model components, there needs to be a method of matching client-side model components with the best server-side model components. A solution to this problem was introduced in the ExpertMatcher (Sharma et al., 2019) framework, which uses autoencoders to match raw data to models. In this work, we propose an extension of ExpertMatcher, where matching can be performed without the need to share the client's raw data representation. The technique is applicable to situations where there are local clients and centralized expert ML models, but the sharing of raw data is constrained.