Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging

• URL: http://arxiv.org/abs/2506.23266v1
• Date: Sun, 29 Jun 2025 14:43:50 GMT
• Title: Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
• Authors: Lujun Li, Zhu Qiyuan, Jiacheng Wang, Wei Li, Hao Gu, Sirui Han, Yike Guo,
• Abstract summary: Sub-MoE is a novel MoE compression framework via Subspace Expert Merging.<n>Our key insight is to perform joint Singular Value Decomposition (SVD) ond expert weights.<n>Our Sub-MoE significantly outperforms existing expert pruning and merging methods.
• Score: 17.490596264046435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture of Experts (MoE) LLMs face significant obstacles due to their massive parameter scale, which imposes memory, storage, and deployment challenges. Although recent expert merging methods promise greater efficiency by consolidating multiple experts, they are fundamentally hindered by parameter conflicts arising from expert specialization. In this paper, we present Sub-MoE, a novel MoE compression framework via Subspace Expert Merging. Our key insight is to perform joint Singular Value Decomposition (SVD) on concatenated expert weights, reducing conflicting parameters by extracting shared $U$-matrices while enabling effective merging of the expert-specific $V$ components. Specifically, Sub-MoE consists of two innovative phases: (1) Adaptive Expert Clustering, which groups functionally coherent experts via K-means clustering based on cosine similarity of expert outputs; and (2) Subspace Expert Merging, which first enforces Experts Union Decomposition to derive the shared $U$-matrix across experts in the same group, then pursues frequency-based merging for individual $V$-matrices, and finalizes expert reconstruction using the merged $V$-matrix. In this way, we align and fuse experts in a shared subspace, and can be extended with intra-expert compression for further inference optimization. Extensive experiments on Mixtral, DeepSeek, and Qwen-1.5|3 MoE LLMs demonstrate that our Sub-MoE significantly outperforms existing expert pruning and merging methods. Notably, our Sub-MoE maintains 96\%|86\% of original performance with 25\%|50\% expert reduction on Mixtral-8x7B in zero-shot benchmarks. Code will be released at https://github.com/lliai/MoERazor.

Related papers

• Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations [48.890534958441016]
  This study investigates domain specialization and expert redundancy in large-scale MoE models.<n>We propose a simple yet effective pruning framework, EASY-EP, to identify and retain only the most relevant experts.<n>Experiments on DeepSeek-R1 and DeepSeek-V3-0324 show that our method can achieve comparable performances and $2.99times$ throughput under the same memory budget with full model with only half the experts.
  arXiv  Detail & Related papers  (2025-04-09T11:34:06Z)
• Convergence Rates for Softmax Gating Mixture of Experts [78.3687645289918]
  Mixture of experts (MoE) has emerged as an effective framework to advance the efficiency and scalability of machine learning models.<n>Central to the success of MoE is an adaptive softmax gating mechanism which takes responsibility for determining the relevance of each expert to a given input and then dynamically assigning experts their respective weights.<n>We perform a convergence analysis of parameter estimation and expert estimation under the MoE equipped with the standard softmax gating or its variants, including a dense-to-sparse gating and a hierarchical softmax gating.
  arXiv  Detail & Related papers  (2025-03-05T06:11:24Z)
• MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition [32.97035551579975]
  We introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. Experiments on Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite, and Mixtral-8$times$7B demonstrate that our proposed methods can both reduce the model size and enhance inference efficiency.
  arXiv  Detail & Related papers  (2024-11-01T20:37:58Z)
• MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts [63.67734699877724]
  MoE++ is a general and heterogeneous MoE framework that integrates both Feed-Forward Network(FFN) and zero-computation experts. MoE++ achieves better performance while delivering 1.1-2.1x expert forward throughput compared to a vanilla MoE model of the same size.
  arXiv  Detail & Related papers  (2024-10-09T18:01:27Z)
• T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning [31.276142111455847]
  Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning.<n>We design a novel framework, mixunderlinetextbfTureunderlinetextbf-of-underlinetextbfRank-onunderlinetextbfE-eunderlinetextbfXper ts (textttT-REX)<n>Rank-1 experts enable a mix-and-match mechanism to quadratically expand the vector subspace of experts with linear parameter overheads, achieving approximate error reduction with optimal
  arXiv  Detail & Related papers  (2024-04-13T12:14:58Z)
• DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models [26.447210565680116]
  We propose the DeepSeekMoE architecture towards ultimate expert specialization. It involves two principal strategies: (1) finely segmenting the experts into $mN$ ones and activating $mK$ from them, allowing for a more flexible combination of activated experts. We show that DeepSeekMoE achieves comparable performance with GShard 2.9B, which has 1.5 times the expert parameters and computation.
  arXiv  Detail & Related papers  (2024-01-11T17:31:42Z)
• Merging Experts into One: Improving Computational Efficiency of Mixture of Experts [71.44422347502409]
  A sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters. Can we retain the advantages of adding more experts without substantially increasing the computational costs? We propose a computation-efficient approach called textbftexttMerging Experts into One (MEO) which reduces the computation cost to that of a single expert.
  arXiv  Detail & Related papers  (2023-10-15T13:28:42Z)
• Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy [84.11508381847929]
  Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks. We propose M-SMoE, which leverages routing statistics to guide expert merging. Our MC-SMoE achieves up to 80% memory and a 20% FLOPs reduction, with virtually no loss in performance.
  arXiv  Detail & Related papers  (2023-10-02T16:51:32Z)
• MoEC: Mixture of Expert Clusters [93.63738535295866]
  Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation.
  arXiv  Detail & Related papers  (2022-07-19T06:09:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.