# Efficient Generalization via Multimodal Co-Training under Data Scarcity and Distribution Shift

arXiv: https://arxiv.org/abs/2510.07509 · HTML: https://mlsanity.com/paper/2510.07509/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 8 Oct 2025.

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

- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [A Survey on Multi-view Learning](https://mlsanity.com/paper/1304.5634/) (2013)
- [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](https://mlsanity.com/paper/2104.05833/) (2021)
- [From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors](https://mlsanity.com/paper/2203.11070/) (2022)
- [Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework](https://mlsanity.com/paper/2302.12247/) (2023)
- [Multimodal Alignment and Fusion: A Survey](https://mlsanity.com/paper/2411.17040/) (2024)
- [Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis](https://mlsanity.com/paper/2109.14595/) (2021)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [Understanding Human Intelligence through Human Limitations](https://mlsanity.com/paper/2009.14050/) (2020)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [A Comprehensive Review of Few-shot Action Recognition](https://mlsanity.com/paper/2407.14744/) (2024)
- [Multi-Label Test-Time Adaptation with Bound Entropy Minimization](https://mlsanity.com/paper/2502.03777/) (2025)
- [Multimodal Fusion Interactions: A Study of Human and Automatic Quantification](https://mlsanity.com/paper/2306.04125/) (2023)
- [Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels](https://mlsanity.com/paper/2403.02746/) (2024)
- [Semantic-aware Video Representation for Few-shot Action Recognition](https://mlsanity.com/paper/2311.06218/) (2023)
- [Generalization Bounds and Stopping Rules for Learning with Self-Selected Data](https://mlsanity.com/paper/2505.07367/) (2025)
- [Out-Of-Domain Unlabeled Data Improves Generalization](https://mlsanity.com/paper/2310.00027/) (2023)

## Abstract (arXiv)

This paper explores a multimodal co-training framework designed to enhance model generalization in situations where labeled data is limited and distribution shifts occur. We thoroughly examine the theoretical foundations of this framework, deriving conditions under which the use of unlabeled data and the promotion of agreement between classifiers for different modalities lead to significant improvements in generalization. We also present a convergence analysis that confirms the effectiveness of iterative co-training in reducing classification errors. In addition, we establish a novel generalization bound that, for the first time in a multimodal co-training context, decomposes and quantifies the distinct advantages gained from leveraging unlabeled multimodal data, promoting inter-view agreement, and maintaining conditional view independence. Our findings highlight the practical benefits of multimodal co-training as a structured approach to developing data-efficient and robust AI systems that can effectively generalize in dynamic, real-world environments. The theoretical foundations are examined in dialogue with, and in advance of, established co-training principles.