EasyDeepLearn

How do you prevent MoE routing collapse?

hard

Answer

  • Without regularization, the router tends to funnel most tokens to a small subset of experts (routing collapse), starving the others.
  • Fixes: (1) auxiliary load-balancing loss penalizing uneven per-expert token counts within a batch; (2) capacity limit — each expert accepts at most 1.25x its 'fair share' of tokens per batch, excess is dropped or routed to other experts; (3) noisy top-k gating (add Gumbel noise) for exploration; (4) expert dropout during training.
Check yourself — multiple choice
  • Nothing needed
  • Aux load-balance loss + capacity cap + noisy gating + expert dropout to prevent routing collapse
  • Increase learning rate
  • MoE naturally balances

MoE balancing: load-balance aux loss + capacity + noisy gating.

#moe#architecture#pretraining

Practise LLMs & GenAI

214 interview questions in this topic.

Related questions