arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.1353stat.MLcs.LG
收藏

多任务课程学习

Curriculum Learning of Multiple Tasks

IST Austria(奥地利科学技术研究所)

Anastasia Pentina, Viktoriia Sharmanska, Christoph H. Lampert

摘要:

在多个任务之间共享信息使算法即使从少量训练数据也能实现良好的泛化性能。然而,在多任务学习的现实场景中,并非所有任务都彼此同等相关,因此仅在最相关的任务之间传输信息可能是有利的。在这项工作中,我们提出了一种方法,处理多个任务的顺序与后续任务之间的共享,而不是共同解决所有的任务。随后,我们解决的问题,课程学习的任务,即找到最好的任务学习顺序。我们的方法是基于一个泛化界标准选择的任务顺序,优化了所有任务的平均预期分类性能。我们的实验结果表明,顺序学习多个相关的任务可以比联合学习它们更有效,任务被解决的顺序会影响整体性能,并且我们的模型能够自动发现任务的有利顺序。

英文摘要:

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover the favourable order of tasks.

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。

↑