# Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks

arXiv: https://arxiv.org/abs/2512.24793 · HTML: https://mlsanity.com/paper/2512.24793/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013)
- [MFAS: Multimodal Fusion Architecture Search](https://mlsanity.com/paper/1903.06496/) (2019)
- [Contrastive Learning Reduces Hallucination in Conversations](https://mlsanity.com/paper/2212.10400/) (2022)
- [BM-NAS: Bilevel Multimodal Neural Architecture Search](https://mlsanity.com/paper/2104.09379/) (2021)
- [Self-supervised Neural Architecture Search](https://mlsanity.com/paper/2007.01500/) (2020)
- [Contrastive Self-supervised Neural Architecture Search](https://mlsanity.com/paper/2102.10557/) (2021)

## Abstract (arXiv)

Neural architecture search (NAS), which automates the architectural design process of deep neural networks (DNN), has attracted increasing attention. Multimodal DNNs that necessitate feature fusion from multiple modalities benefit from NAS due to their structural complexity; however, constructing an architecture for multimodal DNNs through NAS requires a substantial amount of labeled training data. Thus, this paper proposes a self-supervised learning (SSL) method for architecture search of multimodal DNNs. The proposed method applies SSL comprehensively for both the architecture search and model pretraining processes. Experimental results demonstrated that the proposed method successfully designed architectures for DNNs from unlabeled training data.