# Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification

arXiv: https://arxiv.org/abs/2607.24683 · HTML: https://mlsanity.com/paper/2607.24683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Multimodal Contrastive Training for Visual Representation Learning](https://mlsanity.com/paper/2104.12836/) (2021)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [Multimodal Representation Learning by Alternating Unimodal Adaptation](https://mlsanity.com/paper/2311.10707/) (2023)
- [Towards Good Practices for Missing Modality Robust Action Recognition](https://mlsanity.com/paper/2211.13916/) (2022)
- [Gramian Multimodal Representation Learning and Alignment](https://mlsanity.com/paper/2412.11959/) (2024)
- [SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization](https://mlsanity.com/paper/2310.19795/) (2023)
- [Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions](https://mlsanity.com/paper/2107.13782/) (2021)
- [EmbraceNet: A robust deep learning architecture for multimodal classification](https://mlsanity.com/paper/1904.09078/) (2019)
- [SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2507.19264/) (2025)
- [Calibrating Multimodal Learning](https://mlsanity.com/paper/2306.01265/) (2023)
- [DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning](https://mlsanity.com/paper/2408.07080/) (2024)
- [Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach](https://mlsanity.com/paper/2501.01132/) (2025)
- [Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration](https://mlsanity.com/paper/2510.19579/) (2025)

## Abstract (arXiv)

Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance. However, real-world scenarios subject to operational constraints, such as sensor failures or privacy restrictions, lead to inconsistent modality availability between training and inference times. To handle missing modalities, prior studies have mainly covered bimodal data setups and focused on designing robust fusion processes. Instead, we adopt a multi-modal co-learning framework that prioritizes inter-modal collaboration rather than multi-modal fusion. Specifically, we consider that any subset of modalities may be absent, without assuming predefined missing-modality patterns, an inference scenario we refer to as missing arbitrary modalities. To address this challenge, we introduce two alternative approaches that leverage information at both feature- and decision-level. Experiments on two multi-modal classification benchmarks demonstrate significant robustness gains in various missing modality conditions. The first method shows more robust behavior under minimal missing conditions, where a single modality is absent, whereas the second performs better under extreme missing conditions, where all-but-one modalities are missing. Our code is available at https://github.com/fmenat/Co4Miss.