Presenters: Selim Ickin and Jörgen Gustafsson, Ericsson Research
When: 21 June, 2019 - 11:00-12:00 CEST
Where: Adobe Connect (https://collab.switch.ch/qualinet-training)
Machine Learning models in the area of QoE potentially suffer from over-fitting due to limitations including low data volume, and participant profile. This might prevent models being generic if the QoE ML problem is not well formulated, hence these trained models might have risk of performing unexpectedly when tested outside the experimented population. One reason for the limited datasets, which is referred as QoE data lakes, is due to the fact that often these datasets potentially contain user sensitive information, and are only collected throughout expensive user studies with special user consent. Thus, sharing of datasets amongst researchers has been challenging. In this talk, we will discuss on a few state of the art privacy preserving machine learning training techniques that potentially enables sharing of learned knowledge amongst different small data lakes.