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 2202.07304cs.LG
收藏

用于Transformers的XAI:通过保守传播实现更好的简化

XAI for Transformers: Better Explanations through Conservative Propagation

Tel-Aviv University(特拉维夫大学);Technische Universität Berlin(柏林工业大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD——柏林学习与数据基础研究所);Korea University(高丽大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf

摘要:

Transformers已经成为机器学习的重要工具,有着众多的应用。这就需要发展可靠的方法来增加其透明度。已经提出了通常基于梯度信息的多种可解释性方法。我们发现,梯度在一个Transformer反映的功能,只有本地,因此无法可靠地识别输入功能的预测的贡献。我们确定Attention Heads和LayerNorm是这种不可靠解释的主要原因,并提出了一种更稳定的方式通过这些层进行传播。我们的建议,这可以被看作是一个适当的扩展完善的LRP方法Transformers,理论和经验表明,克服了一个简单的基于梯度的方法的不足,并实现了国家的最先进的解释性能上广泛的Transformer模型和数据集。

英文摘要:

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on gradient information, have been proposed. We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. We identify Attention Heads and LayerNorm as main reasons for such unreliable explanations and propose a more stable way for propagation through these layers. Our proposal, which can be seen as a proper extension of the well-established LRP method to Transformers, is shown both theoretically and empirically to overcome the deficiency of a simple gradient-based approach, and achieves state-of-the-art explanation performance on a broad range of Transformer models and datasets.

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。

↑