Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915701309046784 |
|---|---|
| author | Suzuki, Shota Ono, Satoshi |
| author_facet | Suzuki, Shota Ono, Satoshi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_24793 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks Suzuki, Shota Ono, Satoshi Machine Learning Neural and Evolutionary Computing 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. |
| title | Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2512.24793 |