Efficiently approaching vertical federated learning by combining data reduction and conditional computation techniques

In this paper, a framework based on a sparse Mixture of Experts (MoE) architecture is proposed for the federated learning and application of a distributed classification model in domains (like cybersecurity and healthcare) where different parties of the federation store different subsets of features...

Full description

Saved in:
Bibliographic Details
Published in:Journal of big data 2024-05, Vol.11 (1), p.77-37, Article 77
Main Authors: Folino, Francesco, Folino, Gianluigi, Pisani, Francesco Sergio, Pontieri, Luigi, Sabatino, Pietro
Format: Article
Language:English
Subjects:
Big Data
Case Study
Classification
Communications Engineering
Computation
Computational Science and Engineering
Computer Science
Cybersecurity
Data Mining and Knowledge Discovery
Data sampling
Database Management
Deep learning
Federated learning
Green AI
Green and Sustainable AI
Information Storage and Retrieval
Machine learning
Mathematical Applications in Computer Science
Mixture of experts
Networks
Vertical federated learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a framework based on a sparse Mixture of Experts (MoE) architecture is proposed for the federated learning and application of a distributed classification model in domains (like cybersecurity and healthcare) where different parties of the federation store different subsets of features for a number of data instances. The framework is designed to limit the risk of information leakage and computation/communication costs in both model training (through data sampling) and application (leveraging the conditional-computation abilities of sparse MoEs). Experiments on real data have shown the proposed approach to ensure a better balance between efficiency and model accuracy, compared to other VFL-based solutions. Notably, in a real-life cybersecurity case study focused on malware classification (the KronoDroid dataset), the proposed method surpasses competitors even though it utilizes only 50% and 75% of the training set, which is fully utilized by the other approaches in the competition. This method achieves reductions in the rate of false positives by 16.9% and 18.2%, respectively, and also delivers satisfactory results on the other evaluation metrics. These results showcase our framework’s potential to significantly enhance cybersecurity threat detection and prevention in a collaborative yet secure manner.
ISSN:2196-1115
2196-1115
DOI:10.1186/s40537-024-00933-6