# Negative to Positive Co-learning with Aggressive Modality Dropout

arXiv: https://arxiv.org/abs/2501.00865 · HTML: https://mlsanity.com/paper/2501.00865/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jan 2025.

## Built on by (most cited first, 3 of 3)

- [GRAM-DTI: adaptive multimodal representation learning for drug target interaction prediction](https://mlsanity.com/paper/2509.21971/) (2025)
- [MSNN-LINet: Cross-Modal Learning via Continuous Linear Integration](https://mlsanity.com/paper/2606.31135/) (2026)
- [On the Geometry of Multimodal Saturation: Riemannian VICReg](https://mlsanity.com/paper/2610.06096/) (2026)

## Abstract (arXiv)

This paper aims to document an effective way to improve multimodal co-learning by using aggressive modality dropout. We find that by using aggressive modality dropout we are able to reverse negative co-learning (NCL) to positive co-learning (PCL). Aggressive modality dropout can be used to "prep" a multimodal model for unimodal deployment, and dramatically increases model performance during negative co-learning, where during some experiments we saw a 20% gain in accuracy. We also benchmark our modality dropout technique against PCL to show that our modality drop out technique improves co-learning during PCL, although it does not have as much as an substantial effect as it does during NCL. Github: https://github.com/nmagal/modality_drop_for_colearning