FedEmb: A Vertical and Hybrid Federated Learning Algorithm using Network
And Feature Embedding Aggregation
Abstract
Federated learning (FL) is an emerging paradigm for decentralized
training of machine learning models on distributed clients, without
revealing the data to the central server. The learning scheme may be
horizontal, vertical or hybrid (both vertical and horizontal). Most
existing research work with deep neural network (DNN) modeling is
focused on horizontal data distributions, while vertical and hybrid
schemes are much less studied. In this paper, we propose a generalized
algorithm FedEmb, for modeling vertical and hybrid DNN-based learning.
The idea of our algorithm is characterized by higher inference accuracy,
stronger privacy-preserving properties, and lower client-server
communication bandwidth demands as compared with existing work. The
experimental results show that FedEmb is an effective method to tackle
both split feature & subject space decentralized problems. To be
specific, there are 0.3% to 4.2% improvement on inference accuracy and
88.9 % time complexity reduction over baseline method.