@inproceedings{hong-kim-2026-gmoe,
title = "{GM}o{E}: Global Mixture of Experts with Logit Propagation",
author = "Hong, Geonwoo and
Kim, Taehwan",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2065/",
pages = "44599--44614",
ISBN = "979-8-89176-390-6",
abstract = "Sparse Mixture of Experts (SMoE) architectures reduce computational cost by activating only a subset of experts per token, yet they often retain large memory footprints and exhibit significant redundancy, both within and across layers. We propose GMoE, a sparse MoE architecture designed to explicitly address these inefficiencies. Instead of maintaining separate expert sets for each layer, GMoE uses Global Experts shared across all layers and adds a Local Expert per layer for layer-specific adaptation. This architecture reuses Global Experts across layers, thereby mitigating inter-layer redundancy while substantially reducing model parameters. In addition, we introduce a Global Router with a GRU-based recurrent component shared across layers and layer-specific routing heads that propagate routing logits across layers. This routing mechanism couples routing decisions across layers, progressively refines routing paths, and helps mitigate intra-layer redundancy. Across diverse language modeling corpora and downstream benchmarks, GMoE remains competitive while using substantially fewer parameters. Routing path analyses and an ablation study show that GMoE reduces cross-layer routing concentration and increases path diversity, with the Global Experts, the Local Expert, and the Global Router all contributing to the gains. The code is available at https://github.com/GEONWOOHONG/GMoE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-kim-2026-gmoe">
<titleInfo>
<title>GMoE: Global Mixture of Experts with Logit Propagation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geonwoo</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taehwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Sparse Mixture of Experts (SMoE) architectures reduce computational cost by activating only a subset of experts per token, yet they often retain large memory footprints and exhibit significant redundancy, both within and across layers. We propose GMoE, a sparse MoE architecture designed to explicitly address these inefficiencies. Instead of maintaining separate expert sets for each layer, GMoE uses Global Experts shared across all layers and adds a Local Expert per layer for layer-specific adaptation. This architecture reuses Global Experts across layers, thereby mitigating inter-layer redundancy while substantially reducing model parameters. In addition, we introduce a Global Router with a GRU-based recurrent component shared across layers and layer-specific routing heads that propagate routing logits across layers. This routing mechanism couples routing decisions across layers, progressively refines routing paths, and helps mitigate intra-layer redundancy. Across diverse language modeling corpora and downstream benchmarks, GMoE remains competitive while using substantially fewer parameters. Routing path analyses and an ablation study show that GMoE reduces cross-layer routing concentration and increases path diversity, with the Global Experts, the Local Expert, and the Global Router all contributing to the gains. The code is available at https://github.com/GEONWOOHONG/GMoE.</abstract>
<identifier type="citekey">hong-kim-2026-gmoe</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2065/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>44599</start>
<end>44614</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GMoE: Global Mixture of Experts with Logit Propagation
%A Hong, Geonwoo
%A Kim, Taehwan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F hong-kim-2026-gmoe
%X Sparse Mixture of Experts (SMoE) architectures reduce computational cost by activating only a subset of experts per token, yet they often retain large memory footprints and exhibit significant redundancy, both within and across layers. We propose GMoE, a sparse MoE architecture designed to explicitly address these inefficiencies. Instead of maintaining separate expert sets for each layer, GMoE uses Global Experts shared across all layers and adds a Local Expert per layer for layer-specific adaptation. This architecture reuses Global Experts across layers, thereby mitigating inter-layer redundancy while substantially reducing model parameters. In addition, we introduce a Global Router with a GRU-based recurrent component shared across layers and layer-specific routing heads that propagate routing logits across layers. This routing mechanism couples routing decisions across layers, progressively refines routing paths, and helps mitigate intra-layer redundancy. Across diverse language modeling corpora and downstream benchmarks, GMoE remains competitive while using substantially fewer parameters. Routing path analyses and an ablation study show that GMoE reduces cross-layer routing concentration and increases path diversity, with the Global Experts, the Local Expert, and the Global Router all contributing to the gains. The code is available at https://github.com/GEONWOOHONG/GMoE.
%U https://aclanthology.org/2026.acl-long.2065/
%P 44599-44614
Markdown (Informal)
[GMoE: Global Mixture of Experts with Logit Propagation](https://aclanthology.org/2026.acl-long.2065/) (Hong & Kim, ACL 2026)
ACL
- Geonwoo Hong and Taehwan Kim. 2026. GMoE: Global Mixture of Experts with Logit Propagation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 44599–44614, San Diego, California, United States. Association for Computational Linguistics.