paper-with-me

Papers

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) process which feature embeddings (tokens). In this paper, we present a comprehensive study of routers in MoEs for computer vision tasks. We introduce a unified MoE formulation that subsumes different MoEs with two parametric routing tensors. This formulation covers both sparse MoE, which uses a binary or hard assignment between experts and tokens, and soft MoE, which uses a soft assignment between experts and weighted combinations of tokens. Routers for sparse MoEs can be further grouped into two variants: Token Choice, which matches experts to each token, and Expert Choice, which matches tokens to each expert. We conduct head-to-head experiments with 6 different routers, including existing routers from prior work and new ones we introduce. We show that (i) many routers originally developed for language modeling can be adapted to perform strongly in vision tasks, (ii) in sparse MoE, Expert Choice routers generally outperform Token Choice routers, and (iii) soft MoEs generally outperform sparse MoEs with a fixed compute budget. These results provide new insights regarding the crucial role of routers in vision MoE models.

📄 PDF Abstract BibTeX arXiv:2401.15969

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMixture-of-Experts

Similar Papers 제목 키워드 기반

Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts

2026-05-12 · Sagi Ahrac, Noya Hochwald, Mor Geva arxiv

Sparse Mixture-of-Experts (SMoE) models enable scaling language models efficiently, but training them remains challenging, as routing can collapse onto few experts and auxiliary load-balancing losses can reduce specializ…

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

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…

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

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

2024-05-26 · Mohammed Nowaz Rabbani Chowdhury, Meng Wang, Kaoutar El Maghraoui, Naigang Wang 외

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but…

Binary ClassificationMixture-of-Experts