stat.MLApr 2, 2026

BVFLMSP : Bayesian Vertical Federated Learning for Multimodal Survival with Privacy

Authors: Abhilash Kar, Basisth Saha, Tanmay Sen, Biswabrata Pradhan

Organizations: SQC and OR Unit, Indian Statistical Institute, Kolkata, India · Department of Statistics, Presidency University, Kolkata, India

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Multimodal time-to-event prediction often requires integrating sensitive data distributed across multiple parties, making centralized model training impractical due to privacy constraints. At the same time, most existing multimodal survival models produce single deterministic predictions without indicating how confident the model is in its estimates, which can limit their reliability in real-world decision making. To address these challenges, we propose BVFLMSP, a Bayesian Vertical Federated Learning (VFL) framework for multimodal time-to-event analysis based on a Split Neural Network architecture. In BVFLMSP, each client independently models a specific data modality using a Bayesian neural network, while a central server aggregates intermediate representations to perform survival risk prediction. To enhance privacy, we integrate differential privacy mechanisms by perturbing client side representations before transmission, providing formal privacy guarantees against information leakage during federated training. We first evaluate our Bayesian multimodal survival model against widely used single modality survival baselines and the centralized multimodal baseline MultiSurv. Across multimodal settings, the proposed method shows consistent improvements in discrimination performance, with up to 0.02 higher C-index compared to MultiSurv. We then compare federated and centralized learning under varying privacy budgets across different modality combinations, highlighting the tradeoff between predictive performance and privacy. Experimental results show that BVFLMSP effectively includes multimodal data, improves survival prediction over existing baselines, and remains robust under strict privacy constraints while providing uncertainty estimates.

Figures & tables

Figure 1: Architecture of BVFLMSP.
ModelMetricsClinicalmiRNADNAmClinical+ miRNAClinical+ DNAmClinical+ miRNA+ DNAm
CPHC-Index0.6710.6510.649---
 ctd0.6710.6510.644---
 IBS0.1750.1950.187---
 INBLL0.5330.5710.563---
DeepSurvC-Index0.7040.6490.684---
 ctd0.7040.6480.682---
Table 1: Comparison with baseline models on test data
Modalities Combinationϵ\epsilonFederated Learning (FL)Centralized Learning (CL)
  C-Index C-Index 
Clinical + miRNANo DP ( ∞\infty )0.732 0.743 
0.50.547 0.724 
10.559 0.727 
1.50.565 0.731 
100.712 0.734 
Table 2: Comparison of Federated and Centralized Learning under different privacy budgets for various modalities combinations
Figure 2: Loss and accuracy curves for two modalities (Clinical + miRNA).
Figure 3: Loss and accuracy curves for three modalities (Clinical + miRNA + DNAm).
Figure 4: Loss and accuracy curves for two clients (Clinical + miRNA )
Figure 5: Loss and accuracy curves for three clients (Clinical + miRNA + DNAm)
Figure 6: Visual proof of model’s differential privacy
Figure 7: Composition of noise (Bayesian and Embedding output perturbation)
Figure 8: Uncertainty comparison
More in this topic

Multimodal Survival Analysis

Multimodal survival analysis combines imaging, molecular, and clinical data to predict when health events occur and how risk changes over time.

See all 46 papers

Explore similar work

CardsList
Jun 22, 2026

Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data

Survival analysis is central to clinical decision-making, yet reliable time-to-event models require large, diverse cohorts that are rarely available at a single institution, while privacy regulations restrict the centralization of patient data. Federated learning (FL) offers a privacy-preserving alternative by training shared models without exchanging raw data, but its effectiveness for survival modeling under realistic, heterogeneous conditions remains insufficiently understood. This paper presents a systematic, multi-model evaluation of federated survival analysis on a cross-institutional breast cancer cohort with naturally heterogeneous distributed clients. Three representative survival models, the Cox Proportional Hazards model, DeepSurv, and Random Survival Forest (RSF), are compared across centralized, local, and federated training, and three federated optimization strategies (FedAvg, FedProx, and FedAdam) are assessed for the gradient-based models. Results show that FL consistently outperforms local training and approaches, and occasionally exceeds, centralized performance, while RSF offers the best overall balance of discrimination, calibration, and robustness across heterogeneous clients. We further find that performance depends on the diversity of client distributions, and that FedAvg and FedProx are stronger and more stable than FedAdam. Based on these findings, we derive practical, decision-oriented guidelines mapping data, privacy, interpretability, and resource constraints to recommended model and training-paradigm choices for federated survival modeling in healthcare.

Natalia Moreno-Blasco, Anusha Ihalapathirana, Pekka Siirtola +1

Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland · Biomimetics and Intelligent Systems Group, University of Oulu, Oulu, Finland · Faculty of Engineering, University of Deusto, Bilbao, Spain

Cancer Survival PredictionSurvival AnalysisOncologyFederated LearningHeterogeneous Federated Learning
AskPDF
Jun 18, 2026

Evidential Fusion Network for Multimodal Survival Prediction under Missing Modalities

Recent multimodal survival prediction models have demonstrated strong predictive performance by leveraging complementary information across modalities. However, such models generally assume data completeness and exhibit limited robustness toward missing modalities, which are frequently encountered in real-world clinical settings. We propose the Evidential Missing Modality Survival Fusion (EMMS) model for multimodal survival prediction under missing modalities. EMMS offers a straightforward, computationally effective approach to survival analysis without requiring a generative phase for missing data. By employing Dempster-Shafer theory and Gaussian Random Fuzzy Numbers for multimodal decision fusion, it considers both aleatoric and epistemic uncertainty alongside modality reliability for fusion. Moreover, the model treats missing modalities as vacuous evidence, preventing interference with available inputs and naturally reflecting increased uncertainty and calibrated predictions. Extensive experiments on four cancer datasets demonstrate state-of-the-art performance while providing calibrated and interpretable uncertainty estimates under incomplete multimodal observations, without introducing additional computational overhead.

Yucheng Xing, Hailan Mo, Zi Wang +2

National University of Singapore, Singapore · Imperial College London, London, UK

Missing-Modality LearningUncertainty QuantificationCancer Survival PredictionSurvival AnalysisDempster-Shafer TheoryUncertainty-Aware Multimodal Fusion+3
AskPDF
Aug 10, 2026

Multimodal Federated Learning under Dual-Axis Modality Missingness

Multimodal federated learning (FL) supports collaborative modeling in privacy-sensitive health-sensing and medical settings, but realistic deployments often exhibit dual-axis modality missingness: clients have different modality sets, and individual samples may contain only subsets of the modalities available locally. Existing methods typically address these two axes separately. We propose Flux, a multimodal federated learning framework built around two complementary components. First, modality-aware confidence tempering learns sample-specific confidence for each modality through mask-aware unimodal supervision and fuses the confidence estimates from observed modalities into a sample-adaptive temperature that adjusts predictive sharpness according to evidence quality and completeness. Second, gradient-decoupled private adaptation applies this temperature only to a client-private prediction pathway, while training the shared federated model with a standard, untempered objective. This enables sample-specific, client-local confidence adaptation without allowing confidence-dependent gradients to perturb shared representation learning. Across four multimodal datasets, Flux achieves the highest average macro-F1 on every dataset, outperforming the strongest dataset-specific baseline by 0.8~2.2 points and by 1.6 points on average. Additional analyses demonstrate favorable calibration, temperature sensitivity to both modality missingness and input corruption, and more stable shared optimization under private-only tempering. Our code is available at https://github.com/AdibaOrz/Flux.

Adiba Orzikulova, Jaehyun Kwak, Jaemin Shin +5

1KAIST · 2CUHK · 3HKUST

Multimodal Federated LearningMissing-Modality LearningProbability CalibrationFederated LearningHeterogeneous Federated Learning
AskPDF