# Missing-Modality-Aware Graph Neural Network for Cancer Classification

arXiv: https://arxiv.org/abs/2506.22901 · HTML: https://mlsanity.com/paper/2506.22901/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 73 references that are in the map.
- First posted on arXiv 28 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [A System for Massively Parallel Hyperparameter Tuning](https://mlsanity.com/paper/1810.05934/) (2018)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts](https://mlsanity.com/paper/2410.08245/) (2024)
- [MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images](https://mlsanity.com/paper/2207.07027/) (2022)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities](https://mlsanity.com/paper/1807.00123/) (2018)
- [VIGAN: Missing View Imputation with Generative Adversarial Networks](https://mlsanity.com/paper/1708.06724/) (2017)
- [VAEs in the Presence of Missing Data](https://mlsanity.com/paper/2006.05301/) (2020)
- [Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation](https://mlsanity.com/paper/2310.03986/) (2023)
- [Learning Missing Modal Electronic Health Records with Unified Multi-modal Data Embedding and Modality-Aware Attention](https://mlsanity.com/paper/2305.02504/) (2023)
- [Learning from data with structured missingness](https://mlsanity.com/paper/2304.01429/) (2023)
- [MARIA: a Multimodal Transformer Model for Incomplete Healthcare Data](https://mlsanity.com/paper/2412.14810/) (2024)
- [Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2310.20419/) (2023)
- [Multimodal Learning for Multi-Omics: A Survey](https://mlsanity.com/paper/2211.16509/) (2022)

## Abstract (arXiv)

A key challenge in learning from multimodal biological data is missing modalities, where data from one or more modalities are absent for some patients. Existing approaches either exclude patients with missing modalities, impute missing modalities, or make predictions directly with partial modalities. However, most of these methods rely on inflexible, patient-agnostic fusion strategies and do not scale computationally to the combinatorial growth of missing-modality patterns as the number of modalities increases. To address these limitations, we propose MAGNET (Missing-modality-Aware Graph neural NETwork) to enhance multimodal prediction with partial modalities, featuring a dynamic patient-modality multi-head attention mechanism to fuse lower-dimensional modality embeddings based on their contribution and missingness. MAGNET fusion's complexity increases linearly with the number of modalities while adapting to missing-pattern variability. To generate predictions, MAGNET further constructs a patient graph with fused multimodal embeddings as node features and connectivity determined by the modality missingness, followed by a graph neural network. Experiments on three public multiomics datasets for cancer classification, with real-world missingness, show that MAGNET outperforms state-of-the-art fusion methods. The data and code are available at https://github.com/SinaTabakhi/MAGNET.