通过获取对比实例进行主动学习
Active Learning by Acquiring Contrastive Examples
摘要:
主动学习的常见采集函数使用不确定性或多样性采样,旨在分别从未标记数据池中选择困难和多样的数据点。在这项工作中,利用两个世界中最好的,我们提出了一个采集功能,选择选择\textit{contrastive examples},即数据点是相似的模型特征空间,但模型输出最大不同的预测可能性。我们比较了我们的方法,CAL(对比主动学习),在四个自然语言理解任务和七个数据集的一组不同的收购功能。我们的实验表明,CAL在所有任务中,无论是在域内还是域外数据上,都始终优于或等于最佳执行基线。我们还对我们的方法进行了广泛的消融研究,并进一步分析了所有主动获取的数据集,表明CAL与其他策略相比在不确定性和多样性之间实现了更好的权衡。
英文摘要:
Common acquisition functions for active learning use either uncertainty or diversity sampling, aiming to select difficult and diverse data points from the pool of unlabeled data, respectively. In this work, leveraging the best of both worlds, we propose an acquisition function that opts for selecting \textit{contrastive examples}, i.e. data points that are similar in the model feature space and yet the model outputs maximally different predictive likelihoods. We compare our approach, CAL (Contrastive Active Learning), with a diverse set of acquisition functions in four natural language understanding tasks and seven datasets. Our experiments show that CAL performs consistently better or equal than the best performing baseline across all tasks, on both in-domain and out-of-domain data. We also conduct an extensive ablation study of our method and we further analyze all actively acquired datasets showing that CAL achieves a better trade-off between uncertainty and diversity compared to other strategies.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。