paper-with-me

Papers

EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate

2021-12-29 · Xiaonan Nie, Xupeng Miao, Shijie Cao, Lingxiao Ma, Qibin Liu, Jilong Xue, Youshan Miao, Yi Liu, Zhi Yang, Bin Cui

Mixture-of-experts (MoE) is becoming popular due to its success in improving the model quality, especially in Transformers. By routing tokens with a sparse gate to a few experts (i.e., a small pieces of the full model), MoE can easily increase the model parameters to a very large scale while keeping the computation cost in a constant level. Most existing works just initialize some random experts, set a fixed gating strategy (e.g., Top-k), and train the model from scratch in an ad-hoc way. We identify that these MoE models are suffering from the immature experts and unstable sparse gate, which are harmful to the convergence performance. In this paper, we propose an efficient end-to-end MoE training framework called EvoMoE. EvoMoE starts from training one single expert and gradually evolves into a large and sparse MoE structure. EvoMoE mainly contains two phases: the expert-diversify phase to train the base expert for a while and spawn multiple diverse experts from it, and the gate-sparsify phase to learn an adaptive sparse gate and activate a dynamic number of experts. EvoMoE naturally decouples the joint learning of both the experts and the sparse gate and focuses on learning the basic knowledge with a single expert at the early training stage. Then it diversifies the experts and continues to train the MoE with a novel Dense-to-Sparse gate (DTS-Gate). Specifically, instead of using a permanent sparse gate, DTS-Gate begins as a dense gate that routes tokens to all experts, then gradually and adaptively becomes sparser while routes to fewer experts. Evaluations are conducted on three popular models and tasks, including RoBERTa for masked language modeling task, GPT for language modeling task and Transformer for machine translation task. The results show that EvoMoE outperforms existing baselines, including Switch, BASE Layer, Hash Layer and StableMoE.

📄 PDF Abstract BibTeX arXiv:2112.14397

Code (2)

codecaution/evomoe 공식 구현 pytorch
hugozhl/hetu pytorch

Tasks

Language ModelingLanguage ModellingMachine TranslationMasked Language ModelingMixture-of-Experts

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
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…

Similar Papers 제목 키워드 기반

EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models

2025-05-28 · Linglin Jing, Yuting Gao, Zhigang Wang, Wang Lan 외

Recent advancements have shown that the Mixture of Experts (MoE) approach significantly enhances the capacity of large language models (LLMs) and improves performance on downstream tasks. Building on these promising resu…

Mixture-of-ExpertsMMETextVQA

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

2022-03-15 · ACL 2022 5 · Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng 외

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine …

Diversity

MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models

2025-12-13 · Ahmad Chamma, Omar El Herraoui, Guokan Shang arxiv

We introduce MixtureKit, a modular open-source framework for constructing, training, and analyzing Mixture-of-Experts (MoE) models from arbitrary pre-trained or fine-tuned models. MixtureKit currently supports three comp…

Learning Factored Representations in a Deep Mixture of Experts

2013-12-16 · David Eigen, Marc'Aurelio Ranzato, Ilya Sutskever

Mixtures of Experts combine the outputs of several "expert" networks, each of which specializes in a different part of the input space. This is achieved by training a "gating" network that maps each input to a distributi…

Mixture-of-Experts

Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts

2025-09-26 · Naibin Gu, Zhenyu Zhang, Yuchen Feng, Yilong Chen 외 arxiv

Mixture-of-Experts (MoE) models typically fix the number of activated experts $k$ at both training and inference. However, real-world deployments often face heterogeneous hardware, fluctuating workloads, and diverse qual…