# MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health

arXiv: https://arxiv.org/abs/2506.02260 · HTML: https://mlsanity.com/paper/2506.02260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 66 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [Self-Supervised Learning with Swin Transformers](https://mlsanity.com/paper/2105.04553/) (2021)
- [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https://mlsanity.com/paper/2302.00861/) (2023)
- [MST: Masked Self-Supervised Transformer for Visual Representation](https://mlsanity.com/paper/2106.05656/) (2021)
- [How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders](https://mlsanity.com/paper/2210.08344/) (2022)
- [Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data](https://mlsanity.com/paper/2206.02909/) (2022)
- [Ti-MAE: Self-Supervised Masked Time Series Autoencoders](https://mlsanity.com/paper/2301.08871/) (2023)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [The Signature Kernel is the solution of a Goursat PDE](https://mlsanity.com/paper/2006.14794/) (2020)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [Time Series Contrastive Learning with Information-Aware Augmentations](https://mlsanity.com/paper/2303.11911/) (2023)
- [How to Understand Masked Autoencoders](https://mlsanity.com/paper/2202.03670/) (2022)
- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks](https://mlsanity.com/paper/2206.03826/) (2022)
- [Gluformer: Transformer-Based Personalized Glucose Forecasting with Uncertainty Quantification](https://mlsanity.com/paper/2209.04526/) (2022)
- [CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification](https://mlsanity.com/paper/2403.16520/) (2024)

## Abstract (arXiv)

Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data. While self-supervised learning approaches have shown promise for addressing these issues, existing multi-modal extensions present opportunities to better leverage the rich temporal and cross-modal correlations inherent in simultaneously recorded wearable sensor data. We propose the Multi-modal Cross-masked Autoencoder (MoCA), a self-supervised learning framework that combines transformer architecture with masked autoencoder (MAE) methodology, using a principled cross-modality masking scheme that explicitly leverages correlation structures between sensor modalities. MoCA demonstrates strong performance boosts across reconstruction and downstream classification tasks on diverse benchmark datasets. We further establish theoretical guarantees by establishing a fundamental connection between multi-modal MAE loss and kernelized canonical correlation analysis through a Reproducing Kernel Hilbert Space framework, providing principled guidance for correlation-aware masking strategy design. Our approach offers a novel solution for leveraging unlabeled multi-modal wearable data while handling missing modalities, with broad applications across digital health domains.