布线(电子设计自动化)
计算机科学
运筹学
计算机网络
工程类
作者
Quzhe Huang,Zhenwei An,Nan Zhuang,Mingxu Tao,Chen Zhang,Jin Yang,Kun Xu,Kun Xu,Liwei Chen,Songfang Huang,Yansong Feng
出处
期刊:Cornell University - arXiv
日期:2024-03-12
标识
DOI:10.48550/arxiv.2403.07652
摘要
In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty. Unlike traditional MoE approaches that rely on fixed Top-K routing, which activates a predetermined number of experts regardless of the input's complexity, our method dynamically selects experts based on the confidence level in expert selection for each input. This allows for a more efficient utilization of computational resources, activating more experts for complex tasks requiring advanced reasoning and fewer for simpler tasks. Through extensive evaluations, our dynamic routing method demonstrates substantial improvements over conventional Top-2 routing across various benchmarks, achieving an average improvement of 0.7% with less than 90% activated parameters. Further analysis shows our model dispatches more experts to tasks requiring complex reasoning skills, like BBH, confirming its ability to dynamically allocate computational resources in alignment with the input's complexity. Our findings also highlight a variation in the number of experts needed across different layers of the transformer model, offering insights into the potential for designing heterogeneous MoE frameworks. The code and models are available at https://github.com/ZhenweiAn/Dynamic_MoE.
科研通智能强力驱动
Strongly Powered by AbleSci AI