# Sparse Multi-Modal Transformer with Masking for Alzheimer's Disease Classification

arXiv: https://arxiv.org/abs/2512.14491 · HTML: https://mlsanity.com/paper/2512.14491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 5 of 5)

- [Multimodal Attention-based Deep Learning for Alzheimer's Disease Diagnosis](https://mlsanity.com/paper/2206.08826/) (2022)
- [Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction](https://mlsanity.com/paper/2107.09928/) (2021)
- [Cascaded Multi-Modal Mixing Transformers for Alzheimer's Disease Classification with Incomplete Data](https://mlsanity.com/paper/2210.00255/) (2022)
- [A fusion learning method to subgroup analysis of Alzheimer's disease](https://mlsanity.com/paper/2103.06363/) (2021)
- [TriFormer: A Multi-modal Transformer Framework For Mild Cognitive Impairment Conversion Prediction](https://mlsanity.com/paper/2307.07177/) (2023)

## Abstract (arXiv)

Transformer-based multi-modal intelligent systems often suffer from high computational and energy costs due to dense self-attention, limiting their scalability under resource constraints. This paper presents SMMT, a sparse multi-modal transformer architecture designed to improve efficiency and robustness. Building upon a cascaded multi-modal transformer framework, SMMT introduces cluster-based sparse attention to achieve near linear computational complexity and modality-wise masking to enhance robustness against incomplete inputs. The architecture is evaluated using Alzheimer's Disease classification on the ADNI dataset as a representative multi-modal case study. Experimental results show that SMMT maintains competitive predictive performance while significantly reducing training time, memory usage, and energy consumption compared to dense attention baselines, demonstrating its suitability as a resource-aware architectural component for scalable intelligent systems.