Federated Learning with Diverse Tasks and Data

Abstract In this paper, we propose a method for distribu- tively selecting relevant data for a given federated learning task. We use a benchmark model trained on a small benchmark dataset that is task-specific, to evaluate the relevance of individual data samples at each client and select the data with sufficiently high relevance. The effectiveness of our approach is demonstrated experimentally.
Authors
  • Tiffany Tuor (Imperial)
  • Shiqiang Wang (IBM US)
  • Bongjun Ko (IBM US)
  • Changchang Liu (IBM US)
  • Kin Leung (Imperial)
Date Sep-2019
Venue Annual Fall Meeting of the DAIS ITA, 2019