Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets. (arXiv:2202.02794v4 [cs.LG] UPDATED)

Investigating active learning, we focus on the relation between the number of
labeled examples (budget size), and suitable querying strategies. Our
theoretical analysis shows a behavior reminiscent of phase transition: typical
examples are best queried when the budget is low, while unrepresentative
examples are best queried when the budget is large. Combined evidence shows
that a similar phenomenon occurs in common classification models. Accordingly,
we propose TypiClust -- a deep active learning strategy suited for low budgets.
In a comparative …

active learning arxiv budget learning lg strategies