Improving Uncertainty Sampling with Bell Curve Weight Function

arXiv:2403.01352v1 Announce Type: new
Abstract: Typically, a supervised learning model is trained using passive learning by randomly selecting unlabelled instances to annotate. This approach is effective for learning a model, but can be costly in cases where acquiring labelled instances is expensive. For example, it can be time-consuming to manually identify spam mails (labelled instances) from thousands of emails (unlabelled instances) flooding an inbox during initial data collection. Generally, we answer the above scenario with uncertainty sampling, an active learning …

abstract arxiv cases cs.lg example function identify instances sampling spam supervised learning type uncertainty