Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models

• URL: http://arxiv.org/abs/2607.01710v1
• Date: Thu, 02 Jul 2026 05:02:18 GMT
• Title: Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
• Abstract summary: We propose a coverage-aware expert pruning method that uses only generic text corpora for calibration.<n>Our improvements hold with fixed pruning budgets and no downstream calibration data.
• Score: 16.871402640095745
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging. Existing expert-pruning methods typically rely on a single aggregated importance score, which can bias the retained set toward experts favored by dominant calibration patterns. We propose \textbf{Generic TB-Coverage}, a coverage-aware expert pruning method that uses only generic text corpora (WikiText2 and C4) for calibration. Instead of collapsing expert utility into one score, our method profiles per-expert utility separately on each corpus and enforces a fixed-budget coverage rule that preserves high-utility experts from each corpus before constructing the final pruning mask. Across Qwen1.5-MoE-A2.7B and DeepSeek-MoE-16B-Base at 25\%, 50\%, and 75\% retention budgets, our method improves average accuracy on six common zero-shot benchmarks over random pruning, REAP, and ExpertSparsity, while also reducing perplexity degradation on WikiText2 and C4. The gains are largest under aggressive pruning (25\% and 50\% retain), suggesting that preserving cross-corpus expert coverage is an effective generic-data prior for MoE pruning. Our improvements hold with fixed pruning budgets and no downstream calibration data.

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)
• Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models [3.749501286035187]
  We show that renormalization implicitly calibrates expert output gain to the training top-$k$.<n>We find that removing renormalization entirely is catastrophic, showing that preserving a suitable reference mass is crucial.
  arXiv  Detail & Related papers  (2026-09-04T00:11:28Z)
• 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)
• Slicing and Dicing: Configuring Optimal Mixtures of Experts [49.5613403644084]
  We present the first systematic study of over 2,000 pretraining runs spanning models up to 6.6B total parameters.<n>We exhaustively vary total experts, expert dimension, heterogeneous expert sizing within a single layer, shared expert size and load-balancing mechanisms.<n>Our results suggest a simpler recipe: focus on expert count and granularity, other choices have minimal effect on final quality.
  arXiv  Detail & Related papers  (2026-05-12T07:47:22Z)
• Does a Global Perspective Help Prune Sparse MoEs Elegantly? [21.594202826999958]
  Existing pruning methods typically allocate budgets uniformly across layers, overlooking the heterogeneous redundancy that arises in sparse MoEs.<n>We propose GRAPE (Global Redundancy-Aware Pruning of Experts), a global pruning strategy that dynamically allocates pruning budgets based on cross-layer redundancy.<n>Experiments on Mixtral-8x7B, Mixtral-8x22B, DeepSeek-MoE, Qwen-MoE, and GPT-OSS show that, under the same pruning budget, GRAPE consistently achieves the best average performance.
  arXiv  Detail & Related papers  (2026-04-08T00:41:11Z)
• AIMER: Calibration-Free Task-Agnostic MoE Pruning [12.732331870876182]
  We introduce AIMER, a simple calibration-free criterion that yields clear within-layer score separation and distinct expert stratification.<n>Across 7B to 30B MoE language models at 25% and 50% pruning ratios over 16 benchmarks, AIMER consistently delivers competitive or stronger overall performance.
  arXiv  Detail & Related papers  (2026-03-19T04:54:37Z)
• 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)
• REAP the Experts: Why Pruning Prevails for One-Shot MoE compression [5.517309667435783]
  We show that expert pruning is a superior strategy for generative tasks.<n>We propose Router-weighted Expert Activation Pruning (REAP)<n>Our method achieves near-lossless compression on code generation and tool-calling tasks with Qwen3-Coder-480B and Kimi-K2.
  arXiv  Detail & Related papers  (2025-10-15T18:29:28Z)
• Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs [54.95810313530111]
  DERN is a task-agnostic and retraining-free framework for expert pruning and reconstruction.<n>It improves performance by more than 5% on commonsense reasoning and MMLU benchmarks under 50% expert sparsity.
  arXiv  Detail & Related papers  (2025-09-12T16:09:39Z)
• How to Prune Your Language Model: Recovering Accuracy on the "Sparsity May Cry'' Benchmark [60.72725673114168]
  We revisit the question of accurate BERT-pruning during fine-tuning on downstream datasets. We propose a set of general guidelines for successful pruning, even on the challenging SMC benchmark.
  arXiv  Detail & Related papers  (2023-12-21T03:11:30Z)
• Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking [57.42241521034744]
  We propose the concept of certified error control of candidate set pruning for relevance ranking. Our method successfully prunes the first-stage retrieved candidate sets to improve the second-stage reranking speed.
  arXiv  Detail & Related papers  (2022-05-19T16:00:13Z)
• 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.