Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912585364799488 |
|---|---|
| author | Li, Cheng Liu, Jiexiong Chen, Yixuan ji, Jie |
| author_facet | Li, Cheng Liu, Jiexiong Chen, Yixuan ji, Jie |
| contents | Transformer models based on the Mixture of Experts (MoE) architecture have made significant progress in long-sequence modeling, but existing models still have shortcomings in computational efficiency and the ability to capture long-range dependencies, especially in terms of the dynamic adaptability of expert resource allocation. In this paper, we propose a Dynamic Adaptive Shared Expert and Grouped Multi-Head Attention Hybrid Model (DASG-MoE) to enhance long-sequence modeling capabilities by integrating three modules. First, we employ the Grouped Multi-Head Attention (GMHA) mechanism to effectively reduce the computational complexity of long sequences. By parallel processing through sequence grouping, local sliding window attention, and feature aggregation, we address long-range dependency issues and the model's lack of generalization for local information. Second, we design a Dual-Scale Shared Expert Structure (DSSE), where shallow experts use lightweight computations to quickly respond to low-dimensional features, while deep experts process high-dimensional complex semantics through pre-training transfer and post-training optimization, achieving a dynamic balance between efficiency and accuracy. Third, we propose a hierarchical Adaptive Dynamic Routing (ADR) mechanism that dynamically selects expert levels based on feature complexity and task requirements, and optimizes resource allocation through a local expert activation strategy. Experiments on multiple long-sequence benchmark datasets demonstrate that our DASG-MoE model outperforms state-of-the-art models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts Li, Cheng Liu, Jiexiong Chen, Yixuan ji, Jie Machine Learning Artificial Intelligence Transformer models based on the Mixture of Experts (MoE) architecture have made significant progress in long-sequence modeling, but existing models still have shortcomings in computational efficiency and the ability to capture long-range dependencies, especially in terms of the dynamic adaptability of expert resource allocation. In this paper, we propose a Dynamic Adaptive Shared Expert and Grouped Multi-Head Attention Hybrid Model (DASG-MoE) to enhance long-sequence modeling capabilities by integrating three modules. First, we employ the Grouped Multi-Head Attention (GMHA) mechanism to effectively reduce the computational complexity of long sequences. By parallel processing through sequence grouping, local sliding window attention, and feature aggregation, we address long-range dependency issues and the model's lack of generalization for local information. Second, we design a Dual-Scale Shared Expert Structure (DSSE), where shallow experts use lightweight computations to quickly respond to low-dimensional features, while deep experts process high-dimensional complex semantics through pre-training transfer and post-training optimization, achieving a dynamic balance between efficiency and accuracy. Third, we propose a hierarchical Adaptive Dynamic Routing (ADR) mechanism that dynamically selects expert levels based on feature complexity and task requirements, and optimizes resource allocation through a local expert activation strategy. Experiments on multiple long-sequence benchmark datasets demonstrate that our DASG-MoE model outperforms state-of-the-art models. |
| title | Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.10530 |