← Back to all news
arXiv Machine Learning By Ezza Ali, Sehrish Bibi, Momina Moetesum, Faisal Shafait

What We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning

Read the original on arXiv Machine Learning →

The paper investigates training‑free pruning of Mixture‑of‑Experts (MoE) models, focusing on how to handle the computation when a router selects a pruned expert. It compares replacement operators from three families on several models (OLMoE, DeepSeek‑V2‑Lite, Moonlight, Granite) while keeping the pruning mask fixed, and introduces a new operator called the tilted novice. The study finds that no single operator consistently dominates, with performance varying by model, pruning level, and evaluation metric, and it proposes a five‑item checklist for reporting results.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 7

When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models

The paper examines how expert pruning—removing low‑importance experts in Mixture‑of‑Experts models—fails when the router is over‑dispersed, a condition caused by aggressive load‑balancing that spreads tokens nearly uniformly across experts. In this regime, traditional importance signals from router probabilities collapse, making perplexity an unreliable predictor of downstream accuracy; for example, the lowest‑perplexity pruning on gpt‑oss‑20B harms mathematical reasoning while the highest‑perplexity pruning preserves it. To address this, the authors introduce Minimax Expert Score Allocation (MESA), a domain‑aware method that iteratively boosts scores for the most affected domain, achieving minimal worst‑case degradation across domains and outperforming baseline pruning strategies on multiple benchmarks while reducing memory usage.

By Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho, Supriyo Chakraborty, Shi-Xiong Zhang, Sambit Sahu, Milind Naphade
llmsefficiencybenchmarks
More like this →
arXiv AI
Sep 7

ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs

ACE introduces a training‑free, calibration‑free framework for adaptive expert skipping in Mixture‑of‑Experts LLMs. It combines a Global Spectral Proxy that estimates global transformation capacity with a Router‑Conditioned Refinement that builds expert‑specific direction prototypes, enabling the model to skip low‑contribution experts while always keeping the top‑1 expert. Offline computation of expert statistics leaves only lightweight table lookups during inference, and experiments on three MoE‑based LLMs show ACE outperforms static and dynamic baselines, especially at high skipping ratios.

By Zukang Xu, Zhixiong Zhao, Xing Hu, Jiangyong Yu, Houji Wen, Jun Li, Zhe Jiang, Dawei Yang
llmsbenchmarks
More like this →
arXiv Machine Learning
Oct 3

MoRA: MoE Pruning via Router Bias Learning and Expert Approximation

MoRA is a framework for pruning Mixture-of-Experts (MoE) models by learning a router bias for each expert and optimizing it with a language‑modeling loss and a routing‑diversity regularizer. The learned biases sharpen routing distributions to identify critical experts and encourage diverse routing preferences. After pruning, MoRA uses an expert approximation mechanism that approximates the outputs of pruned experts with affine transformations of remaining experts, further improving performance.

By Yushuai Sun, Zikun Zhou, Lin Gao, Jun Yu, Wenjie Pei
efficiencybenchmarkssafety
More like this →