[论文解读] Incremental Sequence Learning

Edwin D. de Jong|arXiv (Cornell University)|Nov 9, 2016

Domain Adaptation and Few-Shot Learning参考文献 20被引用 9

一句话总结

本文提出增量序列学习（ISL），一种基于RNN的序列建模课程学习方法，通过先对序列的较短前缀进行训练，再逐步增加序列长度。ISL将测试误差降低74%，并使性能达到标准序列学习的20倍速，主要归因于通过分阶段训练序列早期部分，提升了RNN的内部表征学习能力。

ABSTRACT

Deep learning research over the past years has shown that by increasing the scope or difficulty of the learning problem over time, increasingly complex learning problems can be addressed. We study incremental learning in the context of sequence learning, using generative RNNs in the form of multi-layer recurrent Mixture Density Networks. While the potential of incremental or curriculum learning to enhance learning is known, indiscriminate application of the principle does not necessarily lead to improvement, and it is essential therefore to know which forms of incremental or curriculum learning have a positive effect. This research contributes to that aim by comparing three instantiations of incremental or curriculum learning. We introduce Incremental Sequence Learning, a simple incremental approach to sequence learning. Incremental Sequence Learning starts out by using only the first few steps of each sequence as training data. Each time a performance criterion has been reached, the length of the parts of the sequences used for training is increased. We introduce and make available a novel sequence learning task and data set: predicting and classifying MNIST pen stroke sequences. We find that Incremental Sequence Learning greatly speeds up sequence learning and reaches the best test performance level of regular sequence learning 20 times faster, reduces the test error by 74%, and in general performs more robustly; it displays lower variance and achieves sustained progress after all three comparison methods have stopped improving. The other instantiations of curriculum learning do not result in any noticeable improvement. A trained sequence prediction model is also used in transfer learning to the task of sequence classification, where it is found that transfer learning realizes improved classification performance compared to methods that learn to classify from scratch.

研究动机与目标

• 探究课程学习是否能提升RNN在序列学习中的性能。
• 评估不同增量学习策略在序列预测任务中的有效性。
• 分析所观察到的性能提升是否源于RNN中表征学习的改进。
• 探索使用ISL训练的模型将序列预测迁移到序列分类任务的可行性。
• 为序列学习研究提供一个可复现的基准，使用MNIST笔画序列数据。

提出的方法

• 该方法在序列的逐步变长前缀上训练一个多层循环混合密度网络（MDN），从仅前几步开始。
• 仅在满足性能标准后才增加训练长度，以确保在增加复杂度前学习稳定。
• 该方法使用一种新型MNIST数字笔画序列数据集，源自数字轮廓，用于评估序列预测性能。
• 与两种替代课程学习方法及标准序列学习进行对比。
• 通过微调ISL训练的序列预测模型，将迁移学习应用于序列分类任务。
• 实验包括使用前馈网络和批量大小变化的消融研究，以隔离RNN特有的序列记忆的贡献。

实验结果

研究问题

• RQ1 与标准训练相比，增量序列学习是否能提升序列建模中的泛化性能？
• RQ2 首先在序列早期部分进行训练，对RNN表征学习有何影响？
• RQ3 其他课程学习策略是否能带来与所提出的ISL方法相似的改进？
• RQ4 通过ISL训练的序列预测模型能否有效迁移到序列分类任务？
• RQ5 RNN记忆在ISL中观察到的性能提升中起到了多大作用？

主要发现

• 与标准序列学习相比，增量序列学习将测试误差降低了74%。
• ISL平均在20倍速内达到标准序列学习的最佳测试性能水平。
• 该方法表现出更低的方差，并在其他方法趋于平台期后仍持续提升。
• 将RNN层替换为前馈网络会消除性能优势，证明了序列记忆的重要性。
• 性能提升并非仅源于批量大小或数据量，因为增加批量大小虽降低但未消除加速效果。
• 使用ISL训练模型进行迁移学习，其分类性能优于从零开始训练的模型。