Repairing Polluted Artificial Intelligent Systems with Machine Unlearning

  This project is intended to seek in-depth understanding of the new promising decentralised machine learning scheme, namely federated learning, and develop a proof-of-concept algorithm-independent unlearning scheme for federated learning. Our new machine unlearning scheme will turn the repair of such polluted artificial intelligent systems on devices, such as smart phones, smart watches, into an environmentally friendly, effortless process, which reduces energy consumption incurred by model retaining and minimises the impact on user experience.

  • Start Date:

    1 December 2019

  • End Date:

    31 July 2021

  • Activity Type:

    Externally Funded Research

  • Funder:

    ENU Development Trust

  • Value:


Project Team