Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
This paper proposes a structural pruning framework for Mixture-of-Experts models by reformulating prune-ratio allocation as a channel-score coverage maximization problem, solved efficiently via attribution-based approximation. Experiments on DeepSeek and Qwen MoE models show accuracy preservation under 50% or 25% structured pruning with 4-bit quantization, achieving 5.27× memory reduction on Qwen3-30B-A3B and outperforming baselines.
[2606.18304] Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
[Submitted on 16 Jun 2026]
Title:Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
View a PDF of the paper titled Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression, by Yifu Ding and 6 other authors
View PDF HTML (experimental)
Abstract:Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead. Prior compression methods mainly operate at the expert level, either removing entire experts or ranking experts by coarse-grained importance scores. However, such expert-wise decisions are often too coarse to capture fine-grained redundancy, leading to misallocated pruning budgets and limited compression. To address this problem, we observe that information within MoE experts is highly concentrated in a small subset of channels, leaving substantial redundancy even in experts deemed important. Based on this observation, we propose a structural pruning framework tailored for MoE models. Our method reformulates prune-ratio allocation as a channel-score coverage maximization problem and solves it efficiently using an attribution-based approximation. Experiments on DeepSeek and Qwen MoE models show that our method preserves model accuracy under 50% or 25% structured pruning when combined with 4-bit quantization. On Qwen3-30B-A3B, our approach reduces memory footprint by 5.27$\times$ and consistently outperforms state-of-the-art baselines across diverse benchmarks.
Comments: 9 pages, 5 figures. Submitted to ICML 2026
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.18304 [cs.LG]
(or arXiv:2606.18304v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.18304
arXiv-issued DOI via DataCite
Submission history
From: Yifu Ding [view email] [v1] Tue, 16 Jun 2026 06:53:27 UTC (5,829 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression, by Yifu Ding and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-06
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
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?)