De-VertiFL: A Solution for Decentralized Vertical Federated Learning

TL;DR

De-VertiFL introduces a decentralized vertical federated learning framework that enhances data privacy and model performance by sharing hidden layer outputs among clients, addressing a gap in existing FL research.

Contribution

It proposes a novel decentralized VFL architecture, a new knowledge exchange scheme, and a distributed training process, improving efficiency and privacy in collaborative learning.

Findings

De-VertiFL outperforms existing methods in F1-score across various datasets.

The approach maintains privacy while enabling effective knowledge sharing.

Experimental results show improved learning efficiency in decentralized VFL settings.

Abstract

Federated Learning (FL), introduced in 2016, was designed to enhance data privacy in collaborative model training environments. Among the FL paradigm, horizontal FL, where clients share the same set of features but different data samples, has been extensively studied in both centralized and decentralized settings. In contrast, Vertical Federated Learning (VFL), which is crucial in real-world decentralized scenarios where clients possess different, yet sensitive, data about the same entity, remains underexplored. Thus, this work introduces De-VertiFL, a novel solution for training models in a decentralized VFL setting. De-VertiFL contributes by introducing a new network architecture distribution, an innovative knowledge exchange scheme, and a distributed federated training process. Specifically, De-VertiFL enables the sharing of hidden layer outputs among federation clients, allowing participants to benefit from intermediate computations, thereby improving learning efficiency. De-VertiFL has been evaluated using a variety of well-known datasets, including both image and tabular data, across binary and multiclass classification tasks. The results demonstrate that De-VertiFL generally surpasses state-of-the-art methods in F1-score performance, while maintaining a decentralized and privacy-preserving framework.