Abstract:
Federated learning (FL) trains a shared collaborative machine learning model using distributed devices to store confidential training data. FL task publishers are monopolists. We present a FL marketplace with multiple FL task publishers and mobile devices for diverse learning tasks. FL task publishers receive pay-as-you-go FL training from mobile devices using blockchain-based cryptocurrencies. In the proposed framework, multiple FL task publishers can compete, and workers (mobile devices) can choose one FL task publisher over another for global model training. Code offloading allows customized FL pipelines in mobile devices and reduces model heterogeneity caused by task publishers’ changing FL tasks. The framework works in experiments.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
