VFedMH: Vertical Federated Learning for Training Multiple Heterogeneous Models

Vertical federated learning has garnered significant attention as it allows clients to train machine learning models collaboratively without sharing local data, which protects the client's local private data. However, existing VFL methods face challenges when dealing with heterogeneous local models among participants, which affects optimization convergence and generalization. To address this challenge, this paper proposes a novel approach called Vertical federated learning for training multiple Heterogeneous models (VFedMH). VFedMH focuses on aggregating the local embeddings of each participant's knowledge during …

attention challenges client convergence cs.ai cs.dc cs.lg data face federated learning machine machine learning machine learning models multiple optimization private data train training