Methods and apparatus for support of vertical federated learning with successive vertical federated learning client information sharing

Abstract

A method for a network data analytics function (NWDAF) vertical federated learning (VFL) client in a wireless communications network, the method comprising: transmitting, to one or more other NWDAF VFL clients, a second training subscribe message 2b; receiving, from the one or more other NWDAF VFL clients, intermediate training results 5c; aggregating the received intermediate training results 5d; performing local computation on the aggregated received intermediate training results to produce a further intermediate training result; and transmitting the further intermediate training result to a network exposure function (NEF) 5a. A VFL server, such as an untrusted application function AF, can transmit to the NEF a first training subscribe message 2a, while a NWDAF client can transmit to an indirect NWDAF VFL client a third subscribe message 2c. The training results can be sent from the NEF to the VFL server 5b. A corresponding method comprising intermediate inferencing results is also disclosed. The methods are related to the 3GPP standards, e.g. for 5G systems. [figure 4f]