paper-with-me

홈 › Papers

CompeteSMoE - Effective Training of Sparse Mixture of Experts via Competition

2024-02-04 · Quang Pham, Giang Do, Huy Nguyen, TrungTin Nguyen, Chenghao Liu, Mina Sartipi, Binh T. Nguyen, Savitha Ramasamy, XiaoLi Li, Steven Hoi, Nhat Ho

Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, effective training of SMoE has proven to be challenging due to the representation collapse issue, which causes parameter redundancy and limited representation potentials. In this work, we propose a competition mechanism to address this fundamental challenge of representation collapse. By routing inputs only to experts with the highest neural response, we show that, under mild assumptions, competition enjoys the same convergence rate as the optimal estimator. We further propose CompeteSMoE, an effective and efficient algorithm to train large language models by deploying a simple router that predicts the competition outcomes. Consequently, CompeteSMoE enjoys strong performance gains from the competition routing policy while having low computation overheads. Our extensive empirical evaluations on two transformer architectures and a wide range of tasks demonstrate the efficacy, robustness, and scalability of CompeteSMoE compared to state-of-the-art SMoE strategies.

📄 PDF Abstract BibTeX arXiv:2402.02526

Code (1)

giangdip2410/competesmoe pytorch

Tasks

Mixture-of-Experts

Similar Papers 제목 키워드 기반

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition

2025-05-19 · Nam V. Nguyen, Huy Nguyen, Quang Pham, Van Nguyen 외

Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, we argue that effective SMoE training remains challengin…

Mixture-of-Experts

Teacher-Guided Routing for Sparse Vision Mixture-of-Experts

2026-04-23 · Masahiro Kada, Ryota Yoshihashi, Satoshi Ikehata, Rei Kawakami 외 arxiv

Recent progress in deep learning has been driven by increasingly large-scale models, but the resulting computational cost has become a critical bottleneck. Sparse Mixture of Experts (MoE) offers an effective solution by …

S2MoE: Robust Sparse Mixture of Experts via Stochastic Learning

2025-03-29 · Giang Do, Hung Le, Truyen Tran

Sparse Mixture of Experts (SMoE) enables efficient training of large language models by routing input tokens to a select number of experts. However, training SMoE remains challenging due to the issue of representation co…

Mixture-of-Experts

From Sparse to Soft Mixtures of Experts

2023-08-02 · Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Neil Houlsby

Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dro…

On the effectiveness of discrete representations in sparse mixture of experts

2024-11-28 · Giang Do, Kha Pham, Hung Le, Truyen Tran

Sparse mixture of experts (SMoE) is an effective solution for scaling up model capacity without increasing the computational costs. A crucial component of SMoE is the router, responsible for directing the input to releva…

Mixture-of-ExpertsQuantization