arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.07887cs.LGcs.CLcs.IRstat.ML
收藏

文本分类中批量大小对停止主动学习的影响

Impact of Batch Size on Stopping Active Learning for Text Classification

The College of New Jersey(新泽西学院)

Garrett Beatty, Ethan Kochis, Michael Bloodgood

摘要:

当使用主动学习时,从学习效率的角度来看,较小的批量通常更有效。然而,在实践中,由于速度和人工注释的考虑,使用更大的批量是必要的。虽然过去的工作表明,从学习曲线的角度来看,较大的批量大小会降低学习效率,但批量大小如何影响停止主动学习的方法仍然是一个悬而未决的问题。我们发现,大批量降低性能的领先停止方法以上的退化,导致学习效率降低。我们分析了这种退化,发现它可以通过改变窗口大小参数来减轻,该参数是在做出停止决策时考虑到过去的学习迭代次数。我们发现,当使用较大的批量大小时,停止方法更有效,当使用较小的窗口大小。

英文摘要:

When using active learning, smaller batch sizes are typically more efficient from a learning efficiency perspective. However, in practice due to speed and human annotator considerations, the use of larger batch sizes is necessary. While past work has shown that larger batch sizes decrease learning efficiency from a learning curve perspective, it remains an open question how batch size impacts methods for stopping active learning. We find that large batch sizes degrade the performance of a leading stopping method over and above the degradation that results from reduced learning efficiency. We analyze this degradation and find that it can be mitigated by changing the window size parameter of how many past iterations of learning are taken into account when making the stopping decision. We find that when using larger batch sizes, stopping methods are more effective when smaller window sizes are used.

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。

↑