# Residual-Guided Expert Specialization for Incomplete Multimodal Learning

arXiv: https://arxiv.org/abs/2606.30355 · HTML: https://mlsanity.com/paper/2606.30355/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 29 Jun 2026.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [HeMIS: Hetero-Modal Image Segmentation](https://mlsanity.com/paper/1607.05194/) (2016)
- [mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation](https://mlsanity.com/paper/2206.02425/) (2022)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts](https://mlsanity.com/paper/2410.08245/) (2024)
- [A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing](https://mlsanity.com/paper/1812.00408/) (2018)
- [MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning](https://mlsanity.com/paper/2304.08028/) (2023)
- [Hallucination Index: An Image Quality Metric for Generative Reconstruction Models](https://mlsanity.com/paper/2407.12780/) (2024)
- [A review of deep learning-based information fusion techniques for multimodal medical image classification](https://mlsanity.com/paper/2404.15022/) (2024)
- [SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2507.19264/) (2025)
- [Imbalanced Big Data Oversampling: Taxonomy, Algorithms, Software, Guidelines and Future Directions](https://mlsanity.com/paper/2107.11508/) (2021)
- [Brain tumor segmentation with missing modalities via latent multi-source correlation representation](https://mlsanity.com/paper/2003.08870/) (2020)
- [Robust Multimodal Learning via Representation Decoupling](https://mlsanity.com/paper/2407.04458/) (2024)
- [OCL: Ordinal Contrastive Learning for Imputating Features with Progressive Labels](https://mlsanity.com/paper/2503.02899/) (2025)
- [Learning Covariance-Based Multi-Scale Representation of Neuroimaging Measures for Alzheimer Classification](https://mlsanity.com/paper/2503.01232/) (2025)

## Abstract (arXiv)

As real-world prediction systems often face missing modalities at inference, incomplete multimodal learning (IML) remains a practical challenge. While prior methods aim to learn representations robust to missing inputs, representations from incomplete modalities inevitably deviate from their full-modality counterparts due to missing evidence. To explicitly leverage these deviations, we propose MARS (Missingness-Aware Residual-guided Specialization), a mixture-of-experts framework that guides expert specialization based on how representations are reshaped by missingness. By contrasting task representations derived from incomplete inputs with their complete counterparts during training, we derive a privileged residual signal that captures this representational gap. The residual signal guides a residual router to assign samples to experts specialized for the corresponding deviation patterns. In parallel, a feature router learns to imitate this routing behavior using only incomplete inputs, enabling deployment without access to full modalities. To mitigate this train-test router gap, we develop a discrepancy-aware noise regularization that adaptively perturbs the residual router's decisions when the feature router deviates, enhancing expert robustness under imperfect imitation. Experiments on multimodal classification (CASIA-SURF, CREMA-D, UPMC Food-101) and segmentation (MCubeS) under missing scenarios show that MARS consistently surpasses baselines while remaining efficient and extensible to diverse backbones and tasks.