# MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning

arXiv: https://arxiv.org/abs/2412.18437 · HTML: https://mlsanity.com/paper/2412.18437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Are we ready for a new paradigm shift? A Survey on Visual Deep MLP](https://mlsanity.com/paper/2111.04060/) (2021)
- [Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture](https://mlsanity.com/paper/2310.12109/) (2023)
- [Deep Multimodal Neural Architecture Search](https://mlsanity.com/paper/2004.12070/) (2020)
- [MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records](https://mlsanity.com/paper/2102.02340/) (2021)
- [BM-NAS: Bilevel Multimodal Neural Architecture Search](https://mlsanity.com/paper/2104.09379/) (2021)
- [HyperMixer: An MLP-based Low Cost Alternative to Transformers](https://mlsanity.com/paper/2203.03691/) (2022)

## Abstract (arXiv)

Choosing a suitable deep learning architecture for multimodal data fusion is a challenging task, as it requires the effective integration and processing of diverse data types, each with distinct structures and characteristics. In this paper, we introduce MixMAS, a novel framework for sampling-based mixer architecture search tailored to multimodal learning. Our approach automatically selects the optimal MLP-based architecture for a given multimodal machine learning (MML) task. Specifically, MixMAS utilizes a sampling-based micro-benchmarking strategy to explore various combinations of modality-specific encoders, fusion functions, and fusion networks, systematically identifying the architecture that best meets the task's performance metrics.