# 3FM: Multi-modal Meta-learning for Federated Tasks

arXiv: https://arxiv.org/abs/2312.10179 · HTML: https://mlsanity.com/paper/2312.10179/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 6 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 6 of 6)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Federated Meta-Learning with Fast Convergence and Efficient Communication](https://mlsanity.com/paper/1802.07876/) (2018)
- [Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation](https://mlsanity.com/paper/1910.13616/) (2019)
- [A New Dataset and Proposed Convolutional Neural Network Architecture for Classification of American Sign Language Digits](https://mlsanity.com/paper/2011.08927/) (2020)

## Built on by (most cited first, 1 of 1)

- [CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2504.18782/) (2025)

## Abstract (arXiv)

We present a novel approach in the domain of federated learning (FL), particularly focusing on addressing the challenges posed by modality heterogeneity, variability in modality availability across clients, and the prevalent issue of missing data. We introduce a meta-learning framework specifically designed for multimodal federated tasks. Our approach is motivated by the need to enable federated models to robustly adapt when exposed to new modalities, a common scenario in FL where clients often differ in the number of available modalities. The effectiveness of our proposed framework is demonstrated through extensive experimentation on an augmented MNIST dataset, enriched with audio and sign language data. We demonstrate that the proposed algorithm achieves better performance than the baseline on a subset of missing modality scenarios with careful tuning of the meta-learning rates. This is a shortened report, and our work will be extended and updated soon.