ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
This addresses the challenge for users in developing countries to access relevant ML models without extensive resources, though it appears incremental as it builds on existing autoencoder and model selection techniques.
The paper tackles the problem of automating deep learning model selection for resource-constrained clients by introducing ExpertMatcher, which uses autoencoders to assign the most relevant pretrained models from a central server based on client data representations, enabling efficient inference without evaluating each model.
In this work we introduce ExpertMatcher, a method for automating deep learning model selection using autoencoders. Specifically, we are interested in performing inference on data sources that are distributed across many clients using pretrained expert ML networks on a centralized server. The ExpertMatcher assigns the most relevant model(s) in the central server given the client's data representation. This allows resource-constrained clients in developing countries to utilize the most relevant ML models for their given task without having to evaluate the performance of each ML model. The method is generic and can be beneficial in any setup where there are local clients and numerous centralized expert ML models.