Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty may not always correlate well with machine interpretation leading to poor performance and exhaustive search is computationally expensive. Addressing these concerns, we propose two classes of techniques to arrange training instances into a learning curriculum based on difficulty scores computed via model-based approaches. The two classes i.e Dataset-level and Instance-level differ in granularity of arrangement. Through comprehensive experiments with 12 datasets, we show that instance-level and dataset-level techniques result in strong representations as they lead to an average performance improvement of 4.17% and 3.15% over their respective baselines. Furthermore, we find that most of this improvement comes from correctly answering the difficult instances, implying a greater efficacy of our techniques on difficult tasks.
翻译:在以往的多任务学习方法中,课程学习战略在困难的等级结构中安排数据集,要么基于人的看法,要么通过彻底地探索最佳安排。然而,人类对困难的看法并不总是与机器解释很好地联系起来,机器解释导致业绩不佳,而详尽的搜索是计算上昂贵的。为了解决这些关切,我们建议采用两类技术,根据以模型为基础的方法计算的困难分数,将培训案例安排在学习课程中。这两类方法,即数据集级别和实例级别,在安排的颗粒性方面各不相同。通过对12个数据集的全面实验,我们发现实例和数据集一级的技术导致强烈的表述,因为它们导致平均业绩改善4.17%和3.15%,高于各自的基线。此外,我们发现,这种改进大多来自正确应对困难情况,意味着我们在困难任务上的技术效率更高。