paper-with-me

Papers

DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models

2024-09-10 · Maryam Akhavan Aghdam, Hongpeng Jin, Yanzhao Wu

Transformer-based Mixture-of-Experts (MoE) models have been driving several recent technological advancements in Natural Language Processing (NLP). These MoE models adopt a router mechanism to determine which experts to activate for routing input tokens. However, existing router mechanisms allocate a fixed number of experts to each token, which neglects the varying importance of different input tokens. In this study, we propose a novel dynamic router mechanism that Dynamically Allocates a variable number of experts for Mixture-of-Experts (DA-MoE) models based on an effective token importance measure. First, we show that the Transformer attention mechanism provides a natural and effective way of calculating token importance. Second, we propose a dynamic router mechanism that effectively decides the optimal number of experts (K) and allocates the top-K experts for each input token. Third, comprehensive experiments on several benchmark datasets demonstrate that our DA-MoE approach consistently outperforms the state-of-the-art Transformer based MoE model on the popular GLUE benchmark.

📄 PDF Abstract BibTeX arXiv:2409.06669

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-Experts

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts

2025-09-30 · Yuan Zhuang, Yi Shen, Yuexin Bian, Qing Su 외 arxiv

Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most exis…

parameter-efficient fine-tuning

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models

2026-01-08 · Guanzhi Deng, Bo Li, Ronghao Chen, Xiujin Liu 외 arxiv

Mixture-of-Experts (MoE) has become a prominent paradigm for scaling Large Language Models (LLMs). Parameter-efficient fine-tuning methods, such as LoRA, are widely adopted to adapt pretrained MoE LLMs to downstream task…

parameter-efficient fine-tuning

Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts

2025-09-05 · Cheng Li, Jiexiong Liu, Yixuan Chen, Jie ji arxiv

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 c…

Computational Efficiency

AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert

2025-11-23 · Yuting Gao, Wang Lan, Hengyuan Zhao, Linjiang Huang 외 arxiv

Multimodal Mixture-of-Experts (MoE) models offer a promising path toward scalable and efficient large vision-language systems. However, existing approaches rely on rigid routing strategies (typically activating a fixed n…

MC#: Mixture Compressor for Mixture-of-Experts Large Models

2025-10-13 · Wei Huang, Yue Liao, Yukang Chen, Jianhui Liu 외 arxiv

Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all experts into memory and activating mult…