# Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervals

arXiv: https://arxiv.org/abs/2602.00171 · HTML: https://mlsanity.com/paper/2602.00171/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 24 of 24)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Conformal Prediction With Conditional Guarantees](https://mlsanity.com/paper/2305.12616/) (2023)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Distributional conformal prediction](https://mlsanity.com/paper/1909.07889/) (2019)
- [MM-RLHF: The Next Step Forward in Multimodal LLM Alignment](https://mlsanity.com/paper/2502.10391/) (2025)
- [Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting](https://mlsanity.com/paper/2502.04395/) (2025)
- [AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2501.16566/) (2025)
- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [A Closer Look at Multimodal Representation Collapse](https://mlsanity.com/paper/2505.22483/) (2025)
- [A Theory of Multimodal Learning](https://mlsanity.com/paper/2309.12458/) (2023)
- [TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning](https://mlsanity.com/paper/2007.06793/) (2020)
- [Scrutinizing XAI using linear ground-truth data with suppressor variables](https://mlsanity.com/paper/2111.07473/) (2021)
- [Vision-Language Models Create Cross-Modal Task Representations](https://mlsanity.com/paper/2410.22330/) (2024)
- [Improving Multimodal Learning Balance and Sufficiency through Data Remixing](https://mlsanity.com/paper/2506.11550/) (2025)
- [On the Convergence of the Shapley Value in Parametric Bayesian Learning Games](https://mlsanity.com/paper/2205.07428/) (2022)
- [Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation](https://mlsanity.com/paper/2504.18539/) (2025)
- [Orthogonalized Kernel Debiased Machine Learning for Multimodal Data Analysis](https://mlsanity.com/paper/2103.07088/) (2021)
- [RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank](https://mlsanity.com/paper/2405.01848/) (2024)
- [Kernel Knockoffs Selection for Nonparametric Additive Models](https://mlsanity.com/paper/2105.11659/) (2021)
- [Prediction via Shapley Value Regression](https://mlsanity.com/paper/2505.04775/) (2025)

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

- [Conditional Validity for Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Group](https://mlsanity.com/paper/2608.15520/) (2026)

## Abstract (arXiv)

Multimodal learning combines information from multiple data modalities to improve predictive performance. However, modalities often contribute unequally and in a data dependent way, making it unclear which data modalities are genuinely informative and to what extent their contributions can be trusted. Quantifying modality level importance together with uncertainty is therefore central to interpretable and reliable multimodal learning. We introduce conformal Shapley intervals, a framework that combines Shapley values with conformal inference to construct uncertainty-aware importance intervals for each modality. Building on these intervals, we propose a modality selection procedure with a provable optimality guarantee: conditional on the observed features, the selected subset of modalities achieves performance close to that of the optimal subset. We demonstrate the effectiveness of our approach on multiple datasets, showing that it provides meaningful uncertainty quantification and strong predictive performance while relying on only a small number of informative modalities.