On the Representation Collapse of Sparse Mixture of Experts. (arXiv:2204.09179v2 [cs.CL] UPDATED)

Sparse mixture of experts provides larger model capacity while requiring a
constant computational overhead. It employs the routing mechanism to distribute
input tokens to the best-matched experts according to their hidden
representations. However, learning such a routing mechanism encourages token
clustering around expert centroids, implying a trend toward representation
collapse. In this work, we propose to estimate the routing scores between
tokens and experts on a low-dimensional hypersphere. We conduct extensive
experiments on cross-lingual language model pre-training and fine-tuning on …

arxiv experts mixture of experts representation