SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs

• URL: http://arxiv.org/abs/2606.09886v1
• Date: Wed, 03 Jun 2026 08:41:48 GMT
• Title: SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs
• Abstract summary: Sparse Mixture-of-Experts (MoE) models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall.<n>We propose textbfSHAPE, a task-driven pruning framework that explicitly models emphintra-layer expert cooperation.
• Score: 4.035485260002141
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall: the full expert pool must remain resident to support token-dependent routing. Expert pruning is a direct remedy, but prior criteria typically score experts independently and overlook that MoE inference is inherently \emph{coalitional}, where outputs arise from routed top-$k$ expert combinations. We propose \textbf{SHAPE}, a task-driven pruning framework that explicitly models \emph{intra-layer} expert cooperation. SHAPE formulates routing traces on a small calibration set as an empirical cooperative game and assigns interaction-aware expert values via a Shapley-style attribution over observed top-$k$ coalitions, enabling the identification of experts that are essential for high-utility collaborations rather than merely frequent. To preserve MoE topology under a global pruning budget, SHAPE further introduces a \emph{quality-coverage} selection rule that retains, in each layer, the minimal expert subset covering an $α$ fraction of non-negative Shapley mass, while using bisection to match a target keep rate. Experiments on three modern MoE backbones (Qwen3-30B-A3B, GPT-OSS-20B, and DeepSeek-V2-Lite) across diverse benchmarks show that SHAPE consistently improves robustness over global and layer-wise pruning variants, maintaining competitive accuracy under 20\% and 40\% expert pruning without additional training and delivering clear reductions in peak GPU memory footprint. The open-source code is available at https://github.com/Alizen-1009/Shapley-Moe.

Related papers

• RAPTOR: Role-Aware Private Training for Mixture-of-Experts [68.5626338219096]
  RAPTOR is a Role-Aware Private Training framework.<n>RAPTOR alternates shared and expert optimization and targets each failure directly.<n> Experiments on Switch Transformer and OLMoE fine-tuning across GLUE tasks, and on DeepSeek-VL2-Tiny, show consistent gains over standard DP baselines.
  arXiv  Detail & Related papers  (2026-09-04T23:16:12Z)
• Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation [49.8459545291965]
  Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.<n>We study this dependency by decomposing sparsely upcycled feed-forward experts into key-value channels.<n>We instantiate it in UniF-MoE, a unified framework for token-adaptive MoE computation.
  arXiv  Detail & Related papers  (2026-08-11T02:40:58Z)
• Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression [74.00650541246374]
  We propose a structural pruning framework tailored for MoE models.<n>Our approach reduces memory footprint by 5.27$times and consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T06:53:27Z)
• ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression [4.740789393042061]
  Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts.<n>We formulate post-training MoE compression as expert-pool consolidation.<n>We propose ConMoE, a train-free prototype remapping framework that selects retained experts.
  arXiv  Detail & Related papers  (2026-05-28T04:44:22Z)
• Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning [14.508049757681862]
  LLM-powered coding agents spend the majority of their token budget reading repository files.<n>We show that this formulation creates a modeling bottleneck.<n>We propose LaMR, a structured pruning framework that decomposes code relevance into two interpretable quality dimensions.
  arXiv  Detail & Related papers  (2026-05-14T18:30:10Z)
• EvoESAP: Non-Uniform Expert Pruning for Sparse MoE [42.738877185877634]
  We present textbfExpected textbfAcceptance textbfProxy (textbfESAP), a speculative-decoding-inspired, teacher-forced metric that measures how well a pruned model matches the full model.<n>We propose EvoESAP, an evolutionary searching framework that optimize a non-uniform layer-wise sparsity allocation under a fixed global budget.
  arXiv  Detail & Related papers  (2026-03-06T08:02:58Z)
• Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs [22.399470395813577]
  Dynamic Expert Sharing (DES) is a novel technique that shifts MoE optimization from token-centric pruning to sequence-level coreset selection.<n>DES reduces unique expert activations by over 55% and latency by up to 38%, while retaining 99% of vanilla accuracy.
  arXiv  Detail & Related papers  (2026-01-31T20:01:47Z)
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping [52.02659589971978]
  We propose MoDES, the first training-free framework that adaptively skips experts to enable efficient and accurate MoE MLLM inference.<n>MoDES significantly enhances inference speed, improving the prefilling time by 2.16$times$ and the decoding time by 1.26$times$.
  arXiv  Detail & Related papers  (2025-11-19T18:48:27Z)
• Unified Sparse Mixture of Experts [14.774596844618396]
  Sparse Mixture of Experts (SMoEs) models scale the capacity of models while maintaining constant computational overhead.<n>This paper proposes a Unified Sparse Mixture of Experts (USMoE) framework that addresses these limitations.
  arXiv  Detail & Related papers  (2025-03-29T07:15:12Z)
• 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)
• Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization [51.98792406392873]
  Mixture of Experts (MoE) provides a powerful way to decompose dense layers into smaller, modular computations. A major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. We propose the Multilinear Mixture of Experts ($mu$MoE) layer to address this, focusing on vision models.
  arXiv  Detail & Related papers  (2024-02-19T21:20:22Z)
• 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)
• MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models [78.45898846056303]
  Pruning is an effective method to reduce the memory footprint and computational cost associated with large natural language processing models. We develop a novel MultiLevel structured Pruning framework, which uses three different levels of structured pruning: head pruning, row pruning, and block-wise sparse pruning.
  arXiv  Detail & Related papers  (2021-05-30T22:00:44Z)

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.