DVFL: A Vertical Federated Learning Method for Dynamic Data

TL;DR

This paper introduces DVFL, a vertical federated learning method that effectively handles dynamic data changes through knowledge distillation, maintaining high performance while preserving data privacy.

Contribution

The paper proposes DVFL, a novel VFL approach that adapts to dynamic data distributions using knowledge distillation, unlike existing static-focused methods.

Findings

DVFL achieves comparable results to static VFL methods in static scenarios.

DVFL effectively adapts to dynamic data distribution changes.

Most computations in DVFL are performed locally for enhanced security.

Abstract

Federated learning, which solves the problem of data island by connecting multiple computational devices into a decentralized system, has become a promising paradigm for privacy-preserving machine learning. This paper studies vertical federated learning (VFL), which tackles the scenarios where collaborating organizations share the same set of users but disjoint features. Contemporary VFL methods are mainly used in static scenarios where the active party and the passive party have all the data from the beginning and will not change. However, the data in real life often changes dynamically. To alleviate this problem, we propose a new vertical federation learning method, DVFL, which adapts to dynamic data distribution changes through knowledge distillation. In DVFL, most of the computations are held locally to improve data security and model efficiency. Our extensive experimental results show that DVFL can not only obtain results close to existing VFL methods in static scenes, but also adapt to changes in data distribution in dynamic scenarios.