BVFLMSP : Bayesian Vertical Federated Learning for Multimodal Survival with Privacy

Abhilash Kar, Basisth Saha, Tanmay Sen, Biswabrata Pradhan|April 2, 2026arXiv

Key Takeaway

This framework enables hospitals and clinics to collaboratively build better survival prediction models without sharing raw patient data, while also quantifying prediction confidence—critical for clinical adoption.

Summary

BVFLMSP combines Bayesian neural networks with federated learning to predict survival outcomes from sensitive multimodal data distributed across multiple parties. Each organization keeps its data private while contributing predictions to a shared model, with added privacy protections and uncertainty estimates for more reliable medical decision-making.

safety multimodal training

Key Terms

federated-learning differential-privacy bayesian-neural-networks multimodal-survival-prediction split-neural-network