English

Mixture of Neuron Experts

Computation and Language 2025-10-08 v1

Abstract

In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE models. For each expert, we rank parameters by the magnitude of their activations from the gate projection and progressively prune the activated subset. Pruning up to 60% of parameters within that subset causes only negligible task-performance degradation; substantial drops occur only after more than 90% are removed. We further decompose experts into neuron-granular MoE and visualize their activation values, finding that most neuron activations are near zero. This observation motivates us to select only high-activation neuron experts during pretraining. Based on this insight, we propose Mixture of Neuron Experts (MoNE). MoNE achieves neuron-granular expert selection by only applying a simple top-k selection within each expert, incurs negligible latency, and requires no additional routing parameters or inter-expert communication. Extensive experiments demonstrate that MoNE matches traditional MoE performance while activating only 50% of the MoE-layer parameters, and it consistently outperforms traditional MoE when compared at equal numbers of activated parameters. These results suggest that MoNE is a practical approach to improving parameter utilization and inference efficiency in MoE-like models.

Keywords

Cite

@article{arxiv.2510.05781,
  title  = {Mixture of Neuron Experts},
  author = {Runxi Cheng and Yuchen Guan and Yucheng Ding and Qingguo Hu and Yongxian Wei and Chun Yuan and Yelong Shen and Weizhu Chen and Yeyun Gong},
  journal= {arXiv preprint arXiv:2510.05781},
  year   = {2025}
}

Comments

18 page, 11 figures, 7 tables

R2 v1 2026-07-01T06:21:01.934Z