Unverified50% confidenceFactExact time
Google于2021年发布的Switch Transformer论文首次证明MoE可将训练效率提升4倍以上
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
Related Claims
UnverifiedThe modern form of MoE can be traced back to a Google paper in 2017, and in 2022 Google's Switch Transformer demonstrated that trillion-parameter sparse models can be trained efficiently.81% similarUnverifiedGoogle于2022年发布的Switch Transformer证明MoE架构在相同计算预算下收敛速度可达稠密模型的4-7倍80% similarUnverifiedMoE混合专家架构最早可追溯至1991年的学术论文，谷歌于2021年发布Switch Transformer将专家数量扩展至2048个75% similarVerifiedThe MoE architecture was proposed by Shazeer et al. in 2017 in the paper "Outrageously Large Neural Networks" and subsequently validated at scale by Google in Switch Transformer (2021)72% similarVerifiedGoogle's Switch Transformer, released in 2021, alleviates load imbalance by simplifying routing to a Top-1 selection and introducing an expert capacity mechanism.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/483356API
curl https://kongchang.com/api/v1/knowledge/claims/483356MCP
get_claim(id=483356)