paper-with-me

홈 › Papers

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

2026-06-10 · Songhao Wu, Ang Lv, Ruobing Xie, Yankai Lin arxiv

Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert matrix into this representative vector, such that its dot-product with token can better reflect token-expert affinity. However, there exists no design principles to enforce this condensation. In this paper, we propose to align each router row with the principal singular direction of the associated expert, as this direction provides the most expressive mathematical description of a matrix. Based on this principle, we propose a router redesign with Manifold Power Iteration (MPI). Specifically, it introduces a "Power-then-Retract" paradigm, where a power iteration step is performed on the router weights, followed by a retraction to impose a norm constraint to ensure both efficiency and stability. Theoretically, we show that MPI drives router rows to converge toward the principal singular directions of associated experts. Empirically, we pretrain MoE model across scales from 1B to 11B parameters to confirm that this alignment facilitates more effective MoE models.

📄 PDF Abstract BibTeX arXiv:2606.12397

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

2025-11-10 · Zhongyang Li, Ziyue Li, Tianyi Zhou arxiv

Sparse Mixture-of-Experts (MoE) have been widely adopted in recent large language models since it can efficiently scale up the model capability without increasing the inference cost. However, evaluations on broad downstr…

Routers in Vision Mixture of Experts: An Empirical Study

2024-01-29 · Tianlin Liu, Mathieu Blondel, Carlos Riquelme, Joan Puigcerver

Mixture-of-Experts (MoE) models are a promising way to scale up model capacity without significantly increasing computational cost. A key component of MoEs is the router, which decides which subset of parameters (experts…

Language ModelingLanguage ModellingMixture-of-Experts

Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling

2025-08-31 · Junfeng Ran, Guangxiang Zhao, Yuhan Wu, Dawei Zhu 외 arxiv

The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. However, efficiently training these models re…

Mixture of Routers

2025-03-30 · Jia-Chen Zhang, Yu-jie Xiong, Xi-He Qiu, Chun-Ming Xia 외

Supervised fine-tuning (SFT) is a milestone in aligning large language models with human instructions and adapting them to downstream tasks. In particular, Low-Rank Adaptation (LoRA) has gained widespread attention due t…

Mixture-of-Expertsparameter-efficient fine-tuning

Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models

2024-12-22 · Elie Antoine, Frédéric Béchet, Philippe Langlais

This study investigates the behavior of model-integrated routers in Mixture of Experts (MoE) models, focusing on how tokens are routed based on their linguistic features, specifically Part-of-Speech (POS) tags. The goal …

Mixture-of-ExpertsPOSSensitivity