Active-Passive Federated Learning for Vertically Partitioned Multi-view Data

TL;DR

This paper introduces a flexible federated learning framework that allows active clients to build models independently while passive clients assist, addressing real-world collaboration challenges in vertically partitioned multi-view data scenarios.

Contribution

It proposes the first active-passive federated learning framework that enables independent inference by active clients, reducing reliance on passive client collaboration during deployment.

Findings

Two classification methods with reconstruction and contrastive loss were effective.

The framework demonstrated robustness in experiments.

Passive clients can assist without being involved in inference.

Abstract

Vertical federated learning is a natural and elegant approach to integrate multi-view data vertically partitioned across devices (clients) while preserving their privacies. Apart from the model training, existing methods requires the collaboration of all clients in the model inference. However, the model inference is probably maintained for service in a long time, while the collaboration, especially when the clients belong to different organizations, is unpredictable in real-world scenarios, such as concellation of contract, network unavailablity, etc., resulting in the failure of them. To address this issue, we, at the first attempt, propose a flexible Active-Passive Federated learning (APFed) framework. Specifically, the active client is the initiator of a learning task and responsible to build the complete model, while the passive clients only serve as assistants. Once the model built, the active client can make inference independently. In addition, we instance the APFed framework into two classification methods with employing the reconstruction loss and the contrastive loss on passive clients, respectively. Meanwhile, the two methods are tested in a set of experiments and achieves desired results, validating their effectiveness.