# PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis

arXiv: https://arxiv.org/abs/2503.04836 · HTML: https://mlsanity.com/paper/2503.04836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 7 of 7)

- [Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2310.01035/) (2023)
- [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)
- [Multi-modal Graph Neural Network for Early Diagnosis of Alzheimer's Disease from sMRI and PET Scans](https://mlsanity.com/paper/2307.16366/) (2023)
- [MultiEYE: Dataset and Benchmark for OCT-Enhanced Retinal Disease Recognition from Fundus Images](https://mlsanity.com/paper/2412.09402/) (2024)
- [Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images](https://mlsanity.com/paper/2308.00291/) (2023)
- [Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data](https://mlsanity.com/paper/2405.07155/) (2024)

## Abstract (arXiv)

Missing modalities pose a major issue in Alzheimer's Disease (AD) diagnosis, as many subjects lack full imaging data due to cost and clinical constraints. While multi-modal learning leverages complementary information, most existing methods train only on complete data, ignoring the large proportion of incomplete samples in real-world datasets like ADNI. This reduces the effective training set and limits the full use of valuable medical data. While some methods incorporate incomplete samples, they fail to effectively address inter-modal feature alignment and knowledge transfer challenges under high missing rates. To address this, we propose a Prototype-Guided Adaptive Distillation (PGAD) framework that directly incorporates incomplete multi-modal data into training. PGAD enhances missing modality representations through prototype matching and balances learning with a dynamic sampling strategy. We validate PGAD on the ADNI dataset with varying missing rates (20%, 50%, and 70%) and demonstrate that it significantly outperforms state-of-the-art approaches. Ablation studies confirm the effectiveness of prototype matching and adaptive sampling, highlighting the potential of our framework for robust and scalable AD diagnosis in real-world clinical settings.