Secure Embedding Aggregation for Federated Representation Learning

Abstract

We consider a federated representation learning framework, where with the assistance of a central server, a group of N distributed clients train collaboratively over their private data, for the representations (or embeddings) of a set of entities (e.g., users in a social network). Under this framework, for the key step of aggregating local embeddings trained privately at the clients, we develop a secure embedding aggregation protocol named , which leverages all potential aggregation opportunities among all the clients, while providing privacy guarantees for the set of local entities and corresponding embeddings simultaneously at each client, against a curious server and up to T < N/2 colluding clients.

Tasks

Reproductions