# BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates

arXiv: https://arxiv.org/abs/2603.19718 · HTML: https://mlsanity.com/paper/2603.19718/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 30 of 37)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/2107.06779/) (2021)
- [Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks](https://mlsanity.com/paper/2202.05306/) (2022)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation](https://mlsanity.com/paper/2203.02177/) (2022)
- [Boosting Multi-modal Model Performance with Adaptive Gradient Modulation](https://mlsanity.com/paper/2308.07686/) (2023)
- [MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance](https://mlsanity.com/paper/2405.17730/) (2024)
- [ReconBoost: Boosting Can Achieve Modality Reconcilement](https://mlsanity.com/paper/2405.09321/) (2024)
- [MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations](https://mlsanity.com/paper/2203.02385/) (2022)
- [Multimodal Fusion on Low-quality Data: A Comprehensive Survey](https://mlsanity.com/paper/2404.18947/) (2024)
- [Enhancing multimodal cooperation via sample-level modality valuation](https://mlsanity.com/paper/2309.06255/) (2023)
- [Diagnosing and Re-learning for Balanced Multimodal Learning](https://mlsanity.com/paper/2407.09705/) (2024)
- [A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations](https://mlsanity.com/paper/2310.20494/) (2023)
- [Classifier-guided Gradient Modulation for Enhanced Multimodal Learning](https://mlsanity.com/paper/2411.01409/) (2024)
- [Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities](https://mlsanity.com/paper/2404.16456/) (2024)
- [MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning](https://mlsanity.com/paper/2303.05338/) (2023)
- [Calibrating Multimodal Learning](https://mlsanity.com/paper/2306.01265/) (2023)

## Built on by (most cited first, 1 of 1)

- [Affect-Prototype Guided Fusion for Open-Vocabulary Incomplete Multi-modal Emotion Recognition](https://mlsanity.com/paper/2609.16962/) (2026)

## Abstract (arXiv)

Learning from multiple modalities often suffers from imbalance, where information-rich modalities dominate optimization while weaker or partially missing modalities contribute less. This imbalance becomes severe in realistic settings with imbalanced missing rates (IMR), where each modality is absent with different probabilities, distorting representation learning and gradient dynamics. We revisit this issue from a training-process perspective and propose BALM, a model-agnostic plug-in framework to achieve balanced multimodal learning under IMR. The framework comprises two complementary modules: the Feature Calibration Module (FCM), which recalibrates unimodal features using global context to establish a shared representation basis across heterogeneous missing patterns; the Gradient Rebalancing Module (GRM), which balances learning dynamics across modalities by modulating gradient magnitudes and directions from both distributional and spatial perspectives. BALM can be seamlessly integrated into diverse backbones, including multimodal emotion recognition (MER) models, without altering their architectures. Experimental results across multiple MER benchmarks confirm that BALM consistently enhances robustness and improves performance under diverse missing and imbalance settings. Code available at: https://github.com/np4s/BALM_CVPR2026.git