|国家预印本平台
首页|GmNet: Revisiting Gating Mechanisms From A Frequency View

GmNet: Revisiting Gating Mechanisms From A Frequency View

GmNet: Revisiting Gating Mechanisms From A Frequency View

来源:Arxiv_logoArxiv
英文摘要

Gating mechanisms have emerged as an effective strategy integrated into model designs beyond recurrent neural networks for addressing long-range dependency problems. In a broad understanding, it provides adaptive control over the information flow while maintaining computational efficiency. However, there is a lack of theoretical analysis on how the gating mechanism works in neural networks. In this paper, inspired by the \textit{convolution theorem}, we systematically explore the effect of gating mechanisms on the training dynamics of neural networks from a frequency perspective. We investigate the interact between the element-wise product and activation functions in managing the responses to different frequency components. Leveraging these insights, we propose a Gating Mechanism Network (GmNet), a lightweight model designed to efficiently utilize the information of various frequency components. It minimizes the low-frequency bias present in existing lightweight models. GmNet achieves impressive performance in terms of both effectiveness and efficiency in the image classification task.

Yifan Wang、Xu Ma、Yitian Zhang、Zhongruo Wang、Sung-Cheol Kim、Vahid Mirjalili、Vidya Renganathan、Yun Fu

计算技术、计算机技术

Yifan Wang,Xu Ma,Yitian Zhang,Zhongruo Wang,Sung-Cheol Kim,Vahid Mirjalili,Vidya Renganathan,Yun Fu.GmNet: Revisiting Gating Mechanisms From A Frequency View[EB/OL].(2025-06-22)[2025-07-16].https://arxiv.org/abs/2503.22841.点此复制

评论