paper-with-me

홈 › Papers

Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules

2025-08-04 · Yilun Liu, Yunpu Ma, Yuetian Lu, Shuo Chen, Zifeng Ding, Volker Tresp arxiv

Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies fail to leverage. This motivates us to investigate whether adaptation modules themselves should incorporate routing mechanisms to align with MoE's multi-expert architecture. We analyze dynamics of core components when applying PEFT to MoE language models and examine how different routing strategies affect adaptation effectiveness. Extensive experiments adapting OLMoE-1B-7B and Mixtral-8x7B on various commonsense and math reasoning tasks validate the performance and efficiency of our routed approach. We identify the optimal configurations for different scenarios and provide empirical analyses with practical insights to facilitate better PEFT and MoE applications.

📄 PDF Abstract BibTeX arXiv:2508.02587

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model

2024-11-12 · Yilun Liu, Yunpu Ma, Shuo Chen, Zifeng Ding 외

The Mixture-of-Experts (MoE) paradigm has emerged as a powerful approach for scaling transformers with improved resource utilization. However, efficiently fine-tuning MoE models remains largely underexplored. Inspired by…

Arithmetic ReasoningMixture-of-Expertsparameter-efficient fine-tuning

Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts

2025-10-08 · Fangshuo Liao, Anastasios Kyrillidis arxiv

Mixture-of-Experts (MoE) architectures have emerged as a cornerstone of modern AI systems. In particular, MoEs route inputs dynamically to specialized experts whose outputs are aggregated through weighted summation. Desp…

MoE-Sieve: Routing-Guided LoRA for Efficient MoE Fine-Tuning

2026-03-25 · Andrea Manzoni arxiv

Standard LoRA fine-tuning of Mixture-of-Experts (MoE) models applies adapters to every expert, yet our profiling shows that per-layer expert routing is highly skewed: a small subset of experts handles most tokens in each…

FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code Generation

2026-05-27 · Loc Pham, Lang Hong Nguyet Anh, Thanh Le-Cong arxiv

Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Haskell, OCaml, and Scala chronically undere…

Code Generation

Mixture-of-Experts with Expert Choice Routing

2022-02-18 · Yanqi Zhou, Tao Lei, Hanxiao Liu, Nan Du 외

Sparsely-activated Mixture-of-experts (MoE) models allow the number of parameters to greatly increase while keeping the amount of computation for a given token or a given sample unchanged. However, a poor expert routing …

Mixture-of-Experts