HybridVFL: Disentangled Feature Learning for Edge-Enabled Vertical Federated Multimodal Classification
By: Mostafa Anoosha , Zeinab Dehghani , Kuniko Paxton and more
Potential Business Impact:
Lets phones learn health secrets without sharing them.
Vertical Federated Learning (VFL) offers a privacy-preserving paradigm for Edge AI scenarios like mobile health diagnostics, where sensitive multimodal data reside on distributed, resource-constrained devices. Yet, standard VFL systems often suffer performance limitations due to simplistic feature fusion. This paper introduces HybridVFL, a novel framework designed to overcome this bottleneck by employing client-side feature disentanglement paired with a server-side cross-modal transformer for context-aware fusion. Through systematic evaluation on the multimodal HAM10000 skin lesion dataset, we demonstrate that HybridVFL significantly outperforms standard federated baselines, validating the criticality of advanced fusion mechanisms in robust, privacy-preserving systems.
Similar Papers
BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity
Machine Learning (CS)
Helps computers learn from mixed data without sharing.
The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications
Machine Learning (CS)
Lets computers learn from private data safely.
X-VFL: A New Vertical Federated Learning Framework with Cross Completion and Decision Subspace Alignment
Machine Learning (CS)
Lets computers learn from incomplete data.