Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks

• URL: http://arxiv.org/abs/2512.24793v1
• Date: Wed, 31 Dec 2025 11:30:28 GMT
• Title: Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
• Authors: Shota Suzuki, Satoshi Ono,
• Abstract summary: This paper proposes a self-supervised learning (SSL) method for architecture search of multimodal deep neural networks (DNNs)<n> Experimental results demonstrated that the proposed method successfully designed architectures for DNNs from unlabeled training data.
• Score: 0.12891210250935145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding [55.5535016040221]
  LM-Searcher is a novel framework for cross-domain neural architecture optimization.<n>Central to our approach is NCode, a universal numerical string representation for neural architectures.<n>Our dataset, encompassing a wide range of architecture-performance pairs, encourages robust and transferable learning.
  arXiv  Detail & Related papers  (2025-09-06T09:26:39Z)
• Multi-Objective Evolutionary Neural Architecture Search for Recurrent Neural Networks [0.0]
  This paper proposes a multi-objective evolutionary algorithm-based RNN architecture search method. The proposed method relies on approximate network morphisms for RNN architecture complexity optimisation during evolution.
  arXiv  Detail & Related papers  (2024-03-17T11:19:45Z)
• A Self-adaptive Neuroevolution Approach to Constructing Deep Neural Network Architectures Across Different Types [5.429458930060452]
  We propose a self-adaptive neuroevolution (SANE) approach to automatically construct various lightweight Deep Neural Network (DNN) architectures for different tasks. One of the key settings in SANE is the search space defined by cells and organs self-adapted to different DNN types. SANE is able to self-adaptively adjust evolution exploration and exploitation to improve search efficiency.
  arXiv  Detail & Related papers  (2022-11-27T07:40:25Z)
• Neural Architecture Search for Spiking Neural Networks [10.303676184878896]
  Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) Most prior SNN methods use ANN-like architectures, which could provide sub-optimal performance for temporal sequence processing of binary information in SNNs. We introduce a novel Neural Architecture Search (NAS) approach for finding better SNN architectures.
  arXiv  Detail & Related papers  (2022-01-23T16:34:27Z)
• Search to aggregate neighborhood for graph neural network [47.47628113034479]
  We propose a framework, which tries to Search to Aggregate NEighborhood (SANE) to automatically design data-specific GNN architectures. By designing a novel and expressive search space, we propose a differentiable search algorithm, which is more efficient than previous reinforcement learning based methods.
  arXiv  Detail & Related papers  (2021-04-14T03:15:19Z)
• NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural Network Synthesis [53.106414896248246]
  We present a framework that allows analysts to effectively build the solution sub-graph space and guide the network search by injecting their domain knowledge. Applying this technique in an iterative manner allows analysts to converge to the best performing neural network architecture for a given application.
  arXiv  Detail & Related papers  (2020-09-28T01:48:45Z)
• Evolving Multi-Resolution Pooling CNN for Monaural Singing Voice Separation [40.170868770930774]
  Monaural Singing Voice Separation (MSVS) is a challenging task and has been studied for decades. Deep neural networks (DNNs) are the current state-of-the-art methods for MSVS. We introduce a Neural Architecture Search (NAS) method to the structure design of DNNs for MSVS.
  arXiv  Detail & Related papers  (2020-08-03T12:09:42Z)
• Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks [61.76338096980383]
  A range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper- parameters of state-of-the-art factored time delay neural networks (TDNNs) These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training. Experiments conducted on a 300-hour Switchboard corpus suggest the auto-configured systems consistently outperform the baseline LF-MMI TDNN systems.
  arXiv  Detail & Related papers  (2020-07-17T08:32:11Z)
• Stage-Wise Neural Architecture Search [65.03109178056937]
  Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These networks consist of stages, which are sets of layers that operate on representations in the same resolution. It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network. However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time.
  arXiv  Detail & Related papers  (2020-04-23T14:16:39Z)
• NAS-Count: Counting-by-Density with Neural Architecture Search [74.92941571724525]
  We automate the design of counting models with Neural Architecture Search (NAS) We introduce an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet)
  arXiv  Detail & Related papers  (2020-02-29T09:18:17Z)
• Modeling Neural Architecture Search Methods for Deep Networks [9.561123408923489]
  We propose a general abstraction model for neural architecture search (NAS) methods. It is possible to compare different design approaches for categorizing and identifying critical areas of interest.
  arXiv  Detail & Related papers  (2019-12-31T05:51:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.