Advances, Systems and Applications
From: A split-federated learning and edge-cloud based efficient and privacy-preserving large-scale item recommendation model
Dataset
# Users
# Items
# Clicks
Density (%)
Item Data Size
MovieLens
6,022
3,043
995,154
5.4%
171Kbytes
Adressa
186,255
14,732
2,103,852
0.07%
Gigabyte