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

arXiv: https://arxiv.org/abs/2506.23266 · HTML: https://mlsanity.com/paper/2506.23266/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 29 Jun 2025.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 30 of 31)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression](https://mlsanity.com/paper/2403.07378/) (2024)
- [Model Fusion via Optimal Transport](https://mlsanity.com/paper/1910.05653/) (2019)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models](https://mlsanity.com/paper/2208.03306/) (2022)
- [Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models](https://mlsanity.com/paper/2402.14800/) (2024)
- [Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy](https://mlsanity.com/paper/2310.01334/) (2023)
- [Optimizing Mode Connectivity via Neuron Alignment](https://mlsanity.com/paper/2009.02439/) (2020)
- [MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router](https://mlsanity.com/paper/2410.12013/) (2024)
- [MoE-I2: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition](https://mlsanity.com/paper/2411.01016/) (2024)
- [Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs](https://mlsanity.com/paper/2407.00945/) (2024)
- [Mixture Compressor for Mixture-of-Experts LLMs Gains More](https://mlsanity.com/paper/2410.06270/) (2024)
- [SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts](https://mlsanity.com/paper/2404.05089/) (2024)
- [Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models](https://mlsanity.com/paper/2406.02924/) (2024)
- [Delta Decompression for MoE-based LLMs Compression](https://mlsanity.com/paper/2502.17298/) (2025)
- [Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts](https://mlsanity.com/paper/2404.05019/) (2024)
- [STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs](https://mlsanity.com/paper/2408.01803/) (2024)
- [STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning](https://mlsanity.com/paper/2409.06211/) (2024)
- [HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts](https://mlsanity.com/paper/2402.12656/) (2024)
- [Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping](https://mlsanity.com/paper/2404.19429/) (2024)
- [Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging](https://mlsanity.com/paper/2406.16330/) (2024)
- [Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning](https://mlsanity.com/paper/2409.01483/) (2024)

## Built on by (most cited first, 28 of 28)

- [REAM: Merging Improves Pruning of Experts in LLMs](https://mlsanity.com/paper/2604.04356/) (2026)
- [PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference](https://mlsanity.com/paper/2511.04805/) (2025)
- [EvoESAP: Non-Uniform Expert Pruning for Sparse MoE](https://mlsanity.com/paper/2603.06003/) (2026)
- [KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models](https://mlsanity.com/paper/2602.11184/) (2026)
- [CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis](https://mlsanity.com/paper/2508.02322/) (2025)
- [MoE Pathfinder: Trajectory-driven Expert Pruning](https://mlsanity.com/paper/2512.18425/) (2025)
- [Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density](https://mlsanity.com/paper/2602.09316/) (2026)
- [IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference](https://mlsanity.com/paper/2605.25475/) (2026)
- [How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle](https://mlsanity.com/paper/2606.15716/) (2026)
- [HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space](https://mlsanity.com/paper/2509.22299/) (2025)
- [Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression](https://mlsanity.com/paper/2510.02345/) (2025)
- [Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs](https://mlsanity.com/paper/2604.07888/) (2026)
- [dMoE: dLLMs with Learnable Block Experts](https://mlsanity.com/paper/2605.30876/) (2026)
- [UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models](https://mlsanity.com/paper/2608.08627/) (2026)
- [ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration](https://mlsanity.com/paper/2608.24938/) (2026)
- [Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective](https://mlsanity.com/paper/2601.11616/) (2026)
- [Concatenated Matrix SVD: Compression Bounds, Incremental Approximation, and Error-Constrained Clustering](https://mlsanity.com/paper/2601.11626/) (2026)
- [Pruning and Distilling Mixture-of-Experts into Dense Language Models](https://mlsanity.com/paper/2605.28207/) (2026)
- [Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing](https://mlsanity.com/paper/2607.28308/) (2026)
- [Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models](https://mlsanity.com/paper/2608.04454/) (2026)
- [Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap](https://mlsanity.com/paper/2605.16349/) (2026)
- [Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression](https://mlsanity.com/paper/2606.18304/) (2026)
- [Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment](https://mlsanity.com/paper/2609.06076/) (2026)
- [SSD-LLaMA: SSD-Native Inference for Trillion-Parameter MoE at 1+ Token/s on a Consumer PC](https://mlsanity.com/paper/2609.18110/) (2026)
- [OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit](https://mlsanity.com/paper/2609.31631/) (2026)
- [EAT: Expert Account Tracker for Efficient MoE Inference](https://mlsanity.com/paper/2609.33614/) (2026)
- [SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining](https://mlsanity.com/paper/2610.03265/) (2026)
- [SLEM: Spectrum-Aware Latent Expert Merging](https://mlsanity.com/paper/2610.16484/) (2026)

## Abstract (arXiv)

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.