Neural Active Learning Beyond Bandits

arXiv:2404.12522v1 Announce Type: new
Abstract: We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learning into a bandit problem, achieving both theoretical and empirical success. However, the performance and computational costs of these methods may be susceptible to the number of classes, denoted as $K$, due to this transformation. Therefore, this paper seeks to answer the question: "How can we mitigate the adverse impacts of $K$ …

abstract active learning arxiv beyond computational costs cs.ai cs.lg however line network neural network performance pool study success type