# Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities

arXiv: https://arxiv.org/abs/2401.03609 · HTML: https://mlsanity.com/paper/2401.03609/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 44 references that are in the map.
- First posted on arXiv 7 Jan 2024.

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [What Makes Multi-modal Learning Better than Single (Provably)](https://mlsanity.com/paper/2106.04538/) (2021)
- [Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation](https://mlsanity.com/paper/1810.04304/) (2018)
- [Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge](https://mlsanity.com/paper/2101.07511/) (2021)
- [Deep learning-based survival prediction for multiple cancer types using histopathology images](https://mlsanity.com/paper/1912.07354/) (2019)
- [Specificity-Preserving Federated Learning for MR Image Reconstruction](https://mlsanity.com/paper/2112.05752/) (2021)
- [Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training](https://mlsanity.com/paper/2111.01338/) (2021)

## Built on by (most cited first, 6 of 6)

- [Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions](https://mlsanity.com/paper/2411.12377/) (2024)
- [Redefining non-IID Data in Federated Learning for Computer Vision Tasks: Migrating from Labels to Embeddings for Task-Specific Data Distributions](https://mlsanity.com/paper/2503.14553/) (2025)
- [The Transition from Centralized Machine Learning to Federated Learning for Mental Health in Education: A Survey of Current Methods and Future Directions](https://mlsanity.com/paper/2501.11714/) (2025)
- [Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion](https://mlsanity.com/paper/2506.22036/) (2025)
- [From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walks](https://mlsanity.com/paper/2509.03709/) (2025)
- [Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges](https://mlsanity.com/paper/2509.07946/) (2025)

## Abstract (arXiv)

The use of machine learning (ML) for cancer staging through medical image analysis has gained substantial interest across medical disciplines. When accompanied by the innovative federated learning (FL) framework, ML techniques can further overcome privacy concerns related to patient data exposure. Given the frequent presence of diverse data modalities within patient records, leveraging FL in a multi-modal learning framework holds considerable promise for cancer staging. However, existing works on multi-modal FL often presume that all data-collecting institutions have access to all data modalities. This oversimplified approach neglects institutions that have access to only a portion of data modalities within the system. In this work, we introduce a novel FL architecture designed to accommodate not only the heterogeneity of data samples, but also the inherent heterogeneity/non-uniformity of data modalities across institutions. We shed light on the challenges associated with varying convergence speeds observed across different data modalities within our FL system. Subsequently, we propose a solution to tackle these challenges by devising a distributed gradient blending and proximity-aware client weighting strategy tailored for multi-modal FL. To show the superiority of our method, we conduct experiments using The Cancer Genome Atlas program (TCGA) datalake considering different cancer types and three modalities of data: mRNA sequences, histopathological image data, and clinical information. Our results further unveil the impact and severity of class-based vs type-based heterogeneity across institutions on the model performance, which widens the perspective to the notion of data heterogeneity in multi-modal FL literature.