Optimizing Server Placement for Vertical Federated Learning in Dynamic Edge/Fog Networks

TL;DR

This paper proposes a novel optimization framework for server placement and resource management in vertical federated learning over dynamic edge/fog networks, improving performance and efficiency.

Contribution

It introduces SC-DN, a method that jointly optimizes server placement, power, and processing in VFL with theoretical guarantees and a practical solver.

Findings

SC-DN converges to a global first-order stationary point.

The method outperforms greedy approaches in accuracy and resource use.

Experiments on image and multi-modal datasets validate effectiveness.

Abstract

We investigate the control and optimization of vertical federated learning (VFL), a class of distributed machine learning (ML) methods in which edge/fog devices contain separate data features, in dynamic edge/fog networks. Owing to heterogeneous data features and hardware across edge/fog networks, devices' contributions to VFL vary substantially, and, moreover, dynamic edge/fog networks can lead to the permanent exit or entry of select data features. In this setting, our proposed methodology, server controlled VFL in dynamic networks (SC-DN), first establishes the existence of a global first-order stationary point for every global round, and then leverages this result to jointly optimize ML model training and resource consumption based on four key control variables: (i) server placement, (ii) device-to-server transmit power, (iii) local device processor frequency, and (iv) local training iterations per global round. The resulting optimization formulation contains coupled variables as well as numerous forms of logarithmic constraints which we show is a mixed-integer signomial program, an NP-hard problem, and for which we develop a general solver. Finally, via experiments on both image and multi-modal datasets, we show that our methodology demonstrates superior classification/regression performance and resource consumption savings than even greedy methodologies.