Multi-Participant Multi-Class Vertical Federated Learning

By Siwei Feng, Han Yu. 2020

98 citations recorded by the source corpus.

Federated learning (FL) is a privacy-preserving paradigm for training collective machine learning models with locally stored data from multiple participants. Vertical federated learning (VFL) deals with the case where participants sharing the same sample ID space but having different feature spaces, while label information is owned by one participant. Current studies of VFL only support two participants, and mostly focus on binaryclass logistic regression problems. In this paper, we propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework for multi-class VFL problems involving multiple parties. Extending the idea of multi-view learning (MVL), MMVFL enables label sharing from its owner to other VFL participants in a privacypreserving manner. To demonstrate the effectiveness of MMVFL, a feature selection scheme is incorporated into MMVFL to compare its performance against supervised feature selection and MVL-based approaches. Experiment results on real-world datasets show that MMVFL can effectively share label information among multiple VFL participants and match multi-class classification performance of existing approaches.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “As demonstrated in Figure 3, FL has various topology deﬁnitions, such as vertical FL [34, 35, 36, 37, 38, 39, 40], split learning [41, 42], decentralized FL [43, 44, 45, 46], and Hierarchical FL [47, 48, 49, 50, 51, 52].”
From distributed machine learning to federated learning: a survey (2021, background): “In order to support multiple parties, the idea of multi-view learning [187] is exploited in a multi-participant, multi-class vertical federated learning framework [42].”
Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, unknown): “The result of the joint modeling is that both parties obtain data protection and jointly improve the model effect without the loss of model [136].”
A Comprehensive Survey of Privacy-preserving Federated Learning (2021, background): “[51] proposed a multi-participant multi-class vertical FL framework.”
Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, methodology): “Our approach is inspired by Reference [18], while the work proposed in Reference [18] aimed at learning multiclass label-sharing model in a privacy-preserving way, and the goal of this study is to process the distributed and heterogeneous multi-view data in a privacy-preserving manner.”
Federated Learning on Non-IID Data: A Survey (2021, background): “Feng and Yu propose an MMVFL framework [32] to solve multi-class problems with multiple parties.”
Vertical Federated Learning: Concepts, Advances, and Challenges (2022, background): “Transfer-learning (TL) based VFL approaches [24], [80], [81], [82], [83] treat the active party A as the source domain with a large corpus of labeled samples and the passive party B as the target domain with only unlabeled samples or a limited amount of labeled samples.”