A brief review of hypernetworks in deep learning
Artificial Intelligence Review · 13.08.2024 · 57 (9)
DOI: 10.1007/s10462-024-10862-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence Review, online erschienen am 13.08.2024. Verfasst von Vinod Kumar Chauhan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 117-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: InnoHK Project Programme, NIHR Oxford Biomedical Research Centre, Pandemic Sciences Institute at the University of Oxford.
Abstract (Originalsprache)
Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility, adaptability, dynamism, faster training, information sharing, and model compression. Hypernets have shown promising results in a variety of deep learning problems, including continual learning, causal inference, transfer learning, weight pruning, uncertainty quantification, zero-shot learning, natural language processing, and reinforcement learning. Despite their success across different problem settings, there is currently no comprehensive review available to inform researchers about the latest developments and to assist in utilizing hypernets. To fill this gap, we review the progress in hypernets. We present an illustrative example of training deep neural networks using hypernets and propose categorizing hypernets based on five design criteria: inputs, outputs, variability of inputs and outputs, and the architecture of hypernets. We also review applications of hypernets across different deep learning problem settings, followed by a discussion of general scenarios where hypernets can be effectively employed. Finally, we discuss the challenges and future directions that remain underexplored in the field of hypernets. We believe that hypernetworks have the potential to revolutionize the field of deep learning. They offer a new way to design and train neural networks, and they have the potential to improve the performance of deep learning models on a variety of tasks. Through this review, we aim to inspire further advancements in deep learning through hypernetworks.
Förderung
- InnoHK Project Programme
- NIHR Oxford Biomedical Research Centre
- Pandemic Sciences Institute at the University of Oxford
Zitieren
APA
Chauhan, V. K., Zhou, J., Lu, P., Molaei, S., & Clifton, D. A. (2024). A brief review of hypernetworks in deep learning. Artificial Intelligence Review, 57(9). https://doi.org/10.1007/s10462-024-10862-8
Vancouver
Chauhan VK, Zhou J, Lu P, Molaei S, Clifton DA. A brief review of hypernetworks in deep learning. Artificial Intelligence Review. 2024;57(9). doi:10.1007/s10462-024-10862-8
BibTeX
@article{Chauhan2024,
author = {Chauhan, Vinod Kumar and Zhou, Jiandong and Lu, Ping and Molaei, Soheila and Clifton, David A.},
title = {A brief review of hypernetworks in deep learning},
journal = {Artificial Intelligence Review},
year = {2024},
volume = {57},
number = {9},
doi = {10.1007/s10462-024-10862-8}
}
EUVIMED