Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Zihan, Huang, Zeyu, Zheng, Bo, Wen, Kaiyue, Wang, Zekun, Men, Rui, Titov, Ivan, Liu, Dayiheng, Zhou, Jingren, Lin, Junyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915135404113920
author Qiu, Zihan
Huang, Zeyu
Zheng, Bo
Wen, Kaiyue
Wang, Zekun
Men, Rui
Titov, Ivan
Liu, Dayiheng
Zhou, Jingren
Lin, Junyang
author_facet Qiu, Zihan
Huang, Zeyu
Zheng, Bo
Wen, Kaiyue
Wang, Zekun
Men, Rui
Titov, Ivan
Liu, Dayiheng
Zhou, Jingren
Lin, Junyang
contents This paper revisits the implementation of $\textbf{L}$oad-$\textbf{b}$alancing $\textbf{L}$oss (LBL) when training Mixture-of-Experts (MoEs) models. Specifically, LBL for MoEs is defined as $N_E \sum_{i=1}^{N_E} f_i p_i$, where $N_E$ is the total number of experts, $f_i$ represents the frequency of expert $i$ being selected, and $p_i$ denotes the average gating score of the expert $i$. Existing MoE training frameworks usually employ the parallel training strategy so that $f_i$ and the LBL are calculated within a $\textbf{micro-batch}$ and then averaged across parallel groups. In essence, a micro-batch for training billion-scale LLMs normally contains very few sequences. So, the micro-batch LBL is almost at the sequence level, and the router is pushed to distribute the token evenly within each sequence. Under this strict constraint, even tokens from a domain-specific sequence ($\textit{e.g.}$, code) are uniformly routed to all experts, thereby inhibiting expert specialization. In this work, we propose calculating LBL using a $\textbf{global-batch}$ to loose this constraint. Because a global-batch contains much more diverse sequences than a micro-batch, which will encourage load balance at the corpus level. Specifically, we introduce an extra communication step to synchronize $f_i$ across micro-batches and then use it to calculate the LBL. Through experiments on training MoEs-based LLMs (up to $\textbf{42.8B}$ total parameters and $\textbf{400B}$ tokens), we surprisingly find that the global-batch LBL strategy yields excellent performance gains in both pre-training perplexity and downstream tasks. Our analysis reveals that the global-batch LBL also greatly improves the domain specialization of MoE experts.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11873
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Qiu, Zihan
Huang, Zeyu
Zheng, Bo
Wen, Kaiyue
Wang, Zekun
Men, Rui
Titov, Ivan
Liu, Dayiheng
Zhou, Jingren
Lin, Junyang
Machine Learning
Computation and Language
This paper revisits the implementation of $\textbf{L}$oad-$\textbf{b}$alancing $\textbf{L}$oss (LBL) when training Mixture-of-Experts (MoEs) models. Specifically, LBL for MoEs is defined as $N_E \sum_{i=1}^{N_E} f_i p_i$, where $N_E$ is the total number of experts, $f_i$ represents the frequency of expert $i$ being selected, and $p_i$ denotes the average gating score of the expert $i$. Existing MoE training frameworks usually employ the parallel training strategy so that $f_i$ and the LBL are calculated within a $\textbf{micro-batch}$ and then averaged across parallel groups. In essence, a micro-batch for training billion-scale LLMs normally contains very few sequences. So, the micro-batch LBL is almost at the sequence level, and the router is pushed to distribute the token evenly within each sequence. Under this strict constraint, even tokens from a domain-specific sequence ($\textit{e.g.}$, code) are uniformly routed to all experts, thereby inhibiting expert specialization. In this work, we propose calculating LBL using a $\textbf{global-batch}$ to loose this constraint. Because a global-batch contains much more diverse sequences than a micro-batch, which will encourage load balance at the corpus level. Specifically, we introduce an extra communication step to synchronize $f_i$ across micro-batches and then use it to calculate the LBL. Through experiments on training MoEs-based LLMs (up to $\textbf{42.8B}$ total parameters and $\textbf{400B}$ tokens), we surprisingly find that the global-batch LBL strategy yields excellent performance gains in both pre-training perplexity and downstream tasks. Our analysis reveals that the global-batch LBL also greatly improves the domain specialization of MoE experts.
title Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2501.11873