SparseFed: Mitigation Model Poisoning Attacks in Federated Learning with Sparsification
Why it's on BrighterTube
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceResearch talk on defending federated learning against model poisoning via sparsification. Teaches robustness techniques for distributed learning.
What you'll learn
A 6-minute video from Google TechTalks: “SparseFed: Mitigation Model Poisoning Attacks in Federated Learning with Sparsification”.
Video by Google TechTalks, played through YouTube's embedded player.
Part of 2021 Google Workshop on Federated Learning and Analytics