đź“’
Pathcheck
  • PathCheck: Privacy-Preserving Crowdsourcing for Citizen Engagement
  • Background
  • Problem
  • Stakeholders
  • Solution
    • The Three Step Process
    • How do we solve the grand challenge?
    • Unique parts of our solution
    • Core Technical Innovation
  • Testimonials
    • Academicians
    • Policymakers/States/Cities
    • Public
  • Privacy Preserved AI for HealthCare
    • Exposure Notification for Automated Contact Tracing (Download only solution)
    • Risk Calculator
    • Secure Multi-Party Computation
    • Differential Privacy
    • Federated and Split Learning
  • Solution Videos
  • The PathCheck Foundation
    • Our Team
    • Team Members
    • Accolades
  • Frequently Asked Questions (FAQs)
  • Our research papers and articles
Powered by GitBook
On this page

Was this helpful?

  1. Privacy Preserved AI for HealthCare

Federated and Split Learning

PreviousDifferential PrivacyNextSolution Videos

Last updated 4 years ago

Was this helpful?

The final technique is federated and split learning. Jane wants to understand which medical treatment for given comorbidity leads to a successful recovery. John’s phone trains a local AI to see how his health status and medical treatment lead to some kind of recovery or hospitalization. Although this local AI will be noisy because it only has data from John. If every user starts calculating such local AI and transmits the local AI parameters to the server. The server can then create the master AI by averaging these multiple local AI parameters.

As you can see, John did not upload his private health data or whether he recovered.

References

[1] Vepakomma, Praneeth, et al. “NoPeek: Information Leakage Reduction to Share Activations in Distributed Deep Learning.” ArXiv:2008.09161 [Cs, Stat], Aug. 2020. arXiv.org, .

http://arxiv.org/abs/2008.09161
Split Learning Project: MIT Media Lab
Federated learningWikipedia
Logo