Scholarlink

Abstract <p>We propose a universal framework for neural network composition based on generative adaptation in a low-dimensional latent space. The method connects two pretrained deep neural networks by introducing an adapter trained with a Wasserstein GAN, enabling knowledge transfer across domains without modifying the original models. We facilitate efficient alignment between neural layers with different semantics and dimensionalities by encoding intermediate representations into a fixed-size latent space via autoencoders. Furthermore, we introduce an improved clustering-based algorithm to detect optimal connection points for both networks and reduce the computational cost. Experiments with models combining pretrained ResNet and DistilBERT networks for image classification and regression tasks demonstrate the validity and advantages of our approach in cross-modal tasks. The adapter achieves high performance with minimal overhead, enabling flexible reuse of pretrained models in new domains without modification of their weights.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Transfer Learning Approach Based on Generative Adaptation of Low-Dimensional Latent Representation

  • 期刊论文

  • 发表日期：

    2025年12月19日

查看全文
  • M. M. Leonov,
  • A. A. Soroka,
  • A. G. Trofimov

摘要

Abstract

We propose a universal framework for neural network composition based on generative adaptation in a low-dimensional latent space. The method connects two pretrained deep neural networks by introducing an adapter trained with a Wasserstein GAN, enabling knowledge transfer across domains without modifying the original models. We facilitate efficient alignment between neural layers with different semantics and dimensionalities by encoding intermediate representations into a fixed-size latent space via autoencoders. Furthermore, we introduce an improved clustering-based algorithm to detect optimal connection points for both networks and reduce the computational cost. Experiments with models combining pretrained ResNet and DistilBERT networks for image classification and regression tasks demonstrate the validity and advantages of our approach in cross-modal tasks. The adapter achieves high performance with minimal overhead, enabling flexible reuse of pretrained models in new domains without modification of their weights.