arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08763cs.CLcs.AI
收藏

通过虚拟对抗训练使注意力机制更加强大和可解释

Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training

Hosei University(法政大学)

Shunsuke Kitada, Hitoshi Iyatomi

摘要:

虽然注意力机制已经成为深度学习模型的基本组成部分,但它们容易受到扰动,这可能会降低预测性能和模型的可解释性。针对注意力机制的对抗性训练(AT)通过考虑对抗性扰动成功地减少了这样的缺点。然而,这种技术需要标签信息,因此,其使用仅限于监督设置。在这项研究中,我们探讨了将虚拟AT(VAT)纳入注意力机制的概念,通过这种机制,即使从未标记的数据中也可以计算对抗性扰动。为了实现这种方法,我们提出了两个一般的训练技术,即增值税的注意力机制(注意力增值税)和“可解释的”增值税的注意力机制(注意力iVAT),扩展AT的注意力机制的半监督设置。特别是,Attention iVAT专注于注意力的差异;因此,它可以有效地学习更清晰的注意力并提高模型的可解释性,即使是未标记的数据。基于六个公共数据集的实证实验表明,我们的技术提供了比传统的基于AT和基于VAT的技术更好的预测性能,并且与人类在检测句子中的重要单词时提供的证据具有更强的一致性。此外,我们的建议提供了这些优点,而不需要添加未标记数据的仔细选择。也就是说,即使使用我们基于VAT的技术的模型是在来自目标任务以外的源的未标记数据上训练的,预测性能和模型的可解释性都可以得到提高。

英文摘要:

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention mechanisms has successfully reduced such drawbacks by considering adversarial perturbations. However, this technique requires label information, and thus, its use is limited to supervised settings. In this study, we explore the concept of incorporating virtual AT (VAT) into the attention mechanisms, by which adversarial perturbations can be computed even from unlabeled data. To realize this approach, we propose two general training techniques, namely VAT for attention mechanisms (Attention VAT) and "interpretable" VAT for attention mechanisms (Attention iVAT), which extend AT for attention mechanisms to a semi-supervised setting. In particular, Attention iVAT focuses on the differences in attention; thus, it can efficiently learn clearer attention and improve model interpretability, even with unlabeled data. Empirical experiments based on six public datasets revealed that our techniques provide better prediction performance than conventional AT-based as well as VAT-based techniques, and stronger agreement with evidence that is provided by humans in detecting important words in sentences. Moreover, our proposal offers these advantages without needing to add the careful selection of unlabeled data. That is, even if the model using our VAT-based technique is trained on unlabeled data from a source other than the target task, both the prediction performance and model interpretability can be improved.

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。

↑