Skip to content
AI News HubLIVE
Original source2 min read

Do Mixture-of-Experts Routers Benefit from Ensembling?

Summary

A new paper investigates whether ensembling multiple routers improves mixture-of-experts models. Testing router ensembles on two image-classification and two tabular-regression tasks, the authors find that more routers lower validation loss and report four concrete findings, though the gains are offset by extra training cost.

SourcearXiv Machine LearningAuthor: Viktor Vesel\'y, Sebastian Jitaru
Do Mixture-of-Experts Routers Benefit from Ensembling?
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

Title:Do Mixture-of-Experts Routers Benefit from Ensembling?

View a PDF of the paper titled Do Mixture-of-Experts Routers Benefit from Ensembling?, by Viktor Vesel\'y and 1 other authors

View PDF HTML (experimental)

Abstract:Ensembles of neural networks have repeatedly been shown to outperform single networks. Ensemble theory attributes this gain to the accuracy of the individual members and the diversity among them. Mixture-of-experts models already combine many experts, but a single router decides how the experts are weighted for each input. Motivated by ensemble theory, we apply ensembling to the routing step: an ensemble of routers, trained jointly with the experts, proposes the expert weights. We systematically evaluate this approach using underparameterized networks on two image-classification and two tabular-regression tasks. We analyse each experiment with a performance-diversity decomposition of the router ensemble, which, to our knowledge, has not previously been developed for routers. We report four findings. First, more routers lower the validation loss. Second, training routers to explicitly maximize expert diversity improves the mean performance on three of the four tasks. Third, explicitly maximizing router diversity has no effect on performance. Fourth, combining router weights with the arithmetic mean works better than combining them with the geometric mean. Routing benefits mildly from ensembling, but this benefit is offset by the computational cost of training additional routers.

Comments: 23 pages, 21 figures

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.17472 [cs.LG]

(or arXiv:2611.17472v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.17472

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Viktor Veselý [view email] [v1] Thu, 12 Nov 2026 19:58:39 UTC (633 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Do Mixture-of-Experts Routers Benefit from Ensembling?, by Viktor Vesel\'y and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Ensembling multiple routers lowered validation loss across a set of small-scale tasks.
  • Training routers to explicitly maximize expert diversity improved mean performance on three of four tasks.
  • Explicitly maximizing router diversity had no effect on performance.
  • Combining router weights with the arithmetic mean beat the geometric mean, but the cost of additional routers offsets the benefit.

Highlights and analysis are generated automatically and may contain errors. Check the original source.