The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence. (arXiv:2112.13121v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2112.13121

Recently, it has been observed that a transfer learning solution might be all
we need to solve many few-shot learning benchmarks -- thus raising important
questions about when and how meta-learning algorithms should be deployed. In
this paper, we seek to clarify these questions by proposing a novel metric --
the diversity coefficient -- to measure the diversity of tasks in a few-shot
learning benchmark. We hypothesize that the diversity coefficient of the
few-shot learning benchmark is predictive of whether …

arxiv diversity failure learning transfer learning