Vertical Federated Learning

Vertical Federated Learning (VFL) is a privacy-preserving machine learning approach enabling collaborative model training across multiple parties holding different features of the same data samples, without directly sharing raw data. Current research emphasizes developing efficient algorithms and model architectures, such as split neural networks and gradient boosting decision trees, to address challenges like communication overhead, security vulnerabilities (including backdoor attacks and data reconstruction attacks), and ensuring fairness in contribution evaluation. VFL's significance lies in its potential to unlock the value of siloed datasets in various sectors (finance, healthcare, IoT) while upholding data privacy regulations, fostering trust, and facilitating collaborative data analysis.