Papers › Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts

Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts

26 Jun 2025arXiv:2506.21328archive 2025-07-28

Jiajie Yang

Mixture-of-Experts (MoE) architectures have emerged as a key strategy for scaling large language models (LLMs) efficiently. However, current MoE systems suffer from severe load imbalance, where only a small subset of experts is consistently activated during training and inference, leading to significant underutilization of model capacity and computational resources. In this work, we revisit expert routing through a clustering perspective and propose Latent Prototype Routing (LPR), a novel routing framework that generalizes existing approaches while promoting balanced expert utilization without compromising downstream performance. Extensive experiments across multiple open-source MoE models -- including DeepSeek-V3, Qwen3-MoE, and Mixtral -- demonstrate that LPR reduces the Gini coefficient of expert load from 0.70 to 0.035 on average, improves the min-max expert load ratio from 1e-6 to 0.70, achieving near-perfect load balancing.

PaperPDFCode

Code

rando11199/latentprototyperouter officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Mixture-of-Experts

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MoE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections