Metraipolis › archive › dc_3362fb45dc4e

Experts Exhibit Structured Redundancy: Structure-Preserving Expert Pruning for Mixture-of-Experts Large Language Models — arXiv:2610.41236

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41236
License (as archived): CC0-1.0
Archived: 2026-11-03T07:11:22.888Z
SHA-256 of the archived text: b1a4d71b10832cb6e3a3b80973e3fb9a07a019e31854bffd99bc0be394428c69
Stable URL of this page: https://metraipolis.com/documento/dc_3362fb45dc4e

How to cite

Experts Exhibit Structured Redundancy: Structure-Preserving Expert Pruning for Mixture-of-Experts Large Language Models — arXiv:2610.41236 — arXiv (en), https://arxiv.org/abs/2610.41236 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3362fb45dc4e (Metraipolis archive dc_3362fb45dc4e, sha256 b1a4d71b10832cb6e3a3b80973e3fb9a07a019e31854bffd99bc0be394428c69)

BibTeX

@misc{dc3362fb45dc4e,
  title = {Experts Exhibit Structured Redundancy: Structure-Preserving Expert Pruning for Mixture-of-Experts Large Language Models — arXiv:2610.41236},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41236},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3362fb45dc4e; sha256 b1a4d71b10832cb6e3a3b80973e3fb9a07a019e31854bffd99bc0be394428c69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41236. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sparse MoE mechanism significantly improves the trade-off between model capacity and inference efficiency. However, practical deployment still requires storing all experts, resulting in substantial memory overhead. We show that expert outputs in MoE layers exhibit structured redundancy. Across different models and task categories, the stable rank and entropy effective rank of expert outputs are consistently far below the nominal number of experts, while expert output distributions also exhibit fewer effective modes. Motivated by these observations, we reformulate expert pruning as a structure-preserving expert subset selection problem and efficiently optimize it via a greedy strategy, rather than only independently scoring and ranking individual experts or exhaustively searching over expert combinations. We propose two expert pruning methods under the unified structure-preserving framework: Projection Energy Expert Pruning (PEEP), which preserves the functional subspace by maximizing weighted projection energy, and Distributional Coverage Expert Pruning (DCEP), which preserves the distributional geometry by minimizing weighted coverage error. Both methods incorporate router-derived weights as priors, enabling them to jointly preserve the global structural relationships among experts while accounting for the local importance of individual experts. Experiments on DeepSeek-V2-Lite and Qwen3-30B-A3B demonstrate that, at the expert retention ratios of 75% and 50%, our methods outperform the state-of-the-art baselines on the majority of benchmarks and consistently achieve the best average performance across both general tasks and mathematical reasoning tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41236 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:09:31.752Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).