# Distributionally Robust Multimodal Machine Learning

arXiv: https://arxiv.org/abs/2511.05716 · HTML: https://mlsanity.com/paper/2511.05716/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Distributionally Robust Logistic Regression](https://mlsanity.com/paper/1509.09259/) (2015)
- [Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework](https://mlsanity.com/paper/2302.12247/) (2023)
- [Regularization via Mass Transportation](https://mlsanity.com/paper/1710.10016/) (2017)
- [Integrated multimodal artificial intelligence framework for healthcare applications](https://mlsanity.com/paper/2202.12998/) (2022)
- [Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation](https://mlsanity.com/paper/2304.01518/) (2023)
- [Distributionally Robust Weighted k-Nearest Neighbors](https://mlsanity.com/paper/2006.04004/) (2020)
- [Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation](https://mlsanity.com/paper/2405.20165/) (2024)
- [Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion](https://mlsanity.com/paper/2412.18024/) (2024)
- [DRO: A Python Library for Distributionally Robust Optimization in Machine Learning](https://mlsanity.com/paper/2505.23565/) (2025)
- [Tractable Uncertainty-Aware Meta-Learning](https://mlsanity.com/paper/2210.01881/) (2022)
- [Creating a Cooperative AI Policymaking Platform through Open Source Collaboration](https://mlsanity.com/paper/2412.06936/) (2024)

## Abstract (arXiv)

We consider the problem of distributionally robust multimodal machine learning. Existing approaches often rely on merging modalities on the feature level (early fusion) or heuristic uncertainty modeling, which downplays modality-aware effects and provide limited insights. We propose a novel distributionally robust optimization (DRO) framework that aims to study both the theoretical and practical insights of multimodal machine learning. We first justify this setup and show the significance of this problem through complexity analysis. We then establish both generalization upper bounds and minimax lower bounds which provide performance guarantees. These results are further extended in settings where we consider encoder-specific error propogations. Empirically, we demonstrate that our approach improves robustness in both simulation settings and real-world datasets. Together, these findings provide a principled foundation for employing multimodal machine learning models in high-stakes applications where uncertainty is unavoidable.