# Attribution Regularization for Multimodal Paradigms

arXiv: https://arxiv.org/abs/2404.02359 · HTML: https://mlsanity.com/paper/2404.02359/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 2 Apr 2024.

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

- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [Improving Multi-Modal Learning with Uni-Modal Teachers](https://mlsanity.com/paper/2106.11059/) (2021)
- [Greedy Gradient Ensemble for Robust Visual Question Answering](https://mlsanity.com/paper/2107.12651/) (2021)
- [MAEA: Multimodal Attribution for Embodied AI](https://mlsanity.com/paper/2307.13850/) (2023)

## Built on by (most cited first, 7 of 7)

- [GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning](https://mlsanity.com/paper/2506.00785/) (2025)
- [Cutting Through the Noise: Boosting LLM Performance on Math Word Problems](https://mlsanity.com/paper/2406.15444/) (2024)
- [MaRVL-QA: A Benchmark for Mathematical Reasoning over Visual Landscapes](https://mlsanity.com/paper/2508.17180/) (2025)
- [The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning](https://mlsanity.com/paper/2510.04141/) (2025)
- [Multimodal Representation Learning and Fusion](https://mlsanity.com/paper/2506.20494/) (2025)
- [Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness](https://mlsanity.com/paper/2509.13332/) (2025)
- [Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition](https://mlsanity.com/paper/2603.13340/) (2026)

## Abstract (arXiv)

Multimodal machine learning has gained significant attention in recent years due to its potential for integrating information from multiple modalities to enhance learning and decision-making processes. However, it is commonly observed that unimodal models outperform multimodal models, despite the latter having access to richer information. Additionally, the influence of a single modality often dominates the decision-making process, resulting in suboptimal performance. This research project aims to address these challenges by proposing a novel regularization term that encourages multimodal models to effectively utilize information from all modalities when making decisions. The focus of this project lies in the video-audio domain, although the proposed regularization technique holds promise for broader applications in embodied AI research, where multiple modalities are involved. By leveraging this regularization term, the proposed approach aims to mitigate the issue of unimodal dominance and improve the performance of multimodal machine learning systems. Through extensive experimentation and evaluation, the effectiveness and generalizability of the proposed technique will be assessed. The findings of this research project have the potential to significantly contribute to the advancement of multimodal machine learning and facilitate its application in various domains, including multimedia analysis, human-computer interaction, and embodied AI research.