DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aghdam, Maryam Akhavan, Jin, Hongpeng, Wu, Yanzhao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912021248737280
author Aghdam, Maryam Akhavan
Jin, Hongpeng
Wu, Yanzhao
author_facet Aghdam, Maryam Akhavan
Jin, Hongpeng
Wu, Yanzhao
contents Transformer-based Mixture-of-Experts (MoE) models have been driving several recent technological advancements in Natural Language Processing (NLP). These MoE models adopt a router mechanism to determine which experts to activate for routing input tokens. However, existing router mechanisms allocate a fixed number of experts to each token, which neglects the varying importance of different input tokens. In this study, we propose a novel dynamic router mechanism that Dynamically Allocates a variable number of experts for Mixture-of-Experts (DA-MoE) models based on an effective token importance measure. First, we show that the Transformer attention mechanism provides a natural and effective way of calculating token importance. Second, we propose a dynamic router mechanism that effectively decides the optimal number of experts (K) and allocates the top-K experts for each input token. Third, comprehensive experiments on several benchmark datasets demonstrate that our DA-MoE approach consistently outperforms the state-of-the-art Transformer based MoE model on the popular GLUE benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2409_06669
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models
Aghdam, Maryam Akhavan
Jin, Hongpeng
Wu, Yanzhao
Machine Learning
Transformer-based Mixture-of-Experts (MoE) models have been driving several recent technological advancements in Natural Language Processing (NLP). These MoE models adopt a router mechanism to determine which experts to activate for routing input tokens. However, existing router mechanisms allocate a fixed number of experts to each token, which neglects the varying importance of different input tokens. In this study, we propose a novel dynamic router mechanism that Dynamically Allocates a variable number of experts for Mixture-of-Experts (DA-MoE) models based on an effective token importance measure. First, we show that the Transformer attention mechanism provides a natural and effective way of calculating token importance. Second, we propose a dynamic router mechanism that effectively decides the optimal number of experts (K) and allocates the top-K experts for each input token. Third, comprehensive experiments on several benchmark datasets demonstrate that our DA-MoE approach consistently outperforms the state-of-the-art Transformer based MoE model on the popular GLUE benchmark.
title DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models
topic Machine Learning
url https://arxiv.org/abs/2409.06669