Mixture of Experts

AI and Machine Learning · Efficiency and Deployment · 2017 · also: MoE · mixture-of-experts.yaml

Routes each token to a few of many expert subnetworks, so parameter count grows without the arithmetic growing with it. The routing is the hard part, and load balance is a training objective of its own.

Colour is the family; a dashed line is the second member of it.

Drag to pan · scroll to zoom · click a node to open it
G mixture-of-experts Mixture of Experts transformer Transformer mixture-of-experts->transformer compute grows with capacity if every weight is used

This node

References