# Communication-Efficient and Robust Multi-Modal Federated Learning via Latent-Space Consensus

arXiv: https://arxiv.org/abs/2603.19067 · HTML: https://mlsanity.com/paper/2603.19067/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Multimodal Federated Learning on IoT Data](https://mlsanity.com/paper/2109.04833/) (2021)
- [Vision-Position Multi-Modal Beam Prediction Using Real Millimeter Wave Datasets](https://mlsanity.com/paper/2111.07574/) (2021)
- [Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach](https://mlsanity.com/paper/2502.01145/) (2025)

## Built on by (most cited first, 2 of 2)

- [SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations](https://mlsanity.com/paper/2605.09485/) (2026)
- [Sheaf-Based Federated Representation Learning](https://mlsanity.com/paper/2608.10016/) (2026)

## Abstract (arXiv)

Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, but applying FL to multi-modal settings introduces significant challenges. Clients typically possess heterogeneous modalities and model architectures, making it difficult to align feature spaces efficiently while preserving privacy and minimizing communication costs. To address this, we introduce CoMFed, a Communication-Efficient Multi-Modal Federated Learning framework that uses learnable projection matrices to generate compressed latent representations. A latent-space regularizer aligns these representations across clients, improving cross-modal consistency and robustness to outliers. Experiments on human activity recognition benchmarks show that CoMFed achieves competitive accuracy with minimal overhead.