GS-MoE: Training-Free MoE Compression via Groupwise Subspace Sharing and Pruning
Overview & Synopsis
Mixture-of-Experts (MoE) models reduce computation through sparse activation, but storing their expert parameters remains a major memory bottleneck. We introduce GS-MoE, a training-free compression framework that addresses redundancy across and within experts through two compression axes: shared-subspace rank and expert intermediate width. Groupwise low-rank representations capture shared structure across experts while retaining expert-specific projections, and Nyström-based neuron compression reduces intermediate width within each expert. For fixed shared subspaces, we derive per-expert reconstruction-error reductions from the reconstruction objective and use them to guide expert grouping. Budgets are allocated hierarchically using a gradient-free layer-importance score to guide the allocation of rank and width budgets across layers, which eigenvalues and leverage then distribute as non-uniform ranks across groups and intermediate widths across experts. Experiments demonstrate the complementary benefits of compression along both axes, particularly at high compression rates on fine-grained MoE models. On DeepSeek-MoE-16B-Base, at a 60% reduction in total model parameters, GS-MoE retains approximately 90% of the uncompressed model's average reasoning performance, compared with 73% for D$^2$-MoE, while achieving 20% lower out-of-domain perplexity. We provide a code implementation at: https://github.com/cbacary/GS-MoE
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | GS-MoE: Training-Free MoE Compression via Groupwise Subspace Sharing and Pruning |
|---|---|
| Author / Organization | Carson Cary, Yukai Jin, Yihao Huang, Zhankai Ye, Fangyi Li, Ting Hua, Xin Liu, Shangqian Gao |
| Subject & Discipline | cs.LG |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-262416 |
| Original Source Link | Visit Source Page on arxiv.org » |