Apart from the high accuracy of machine learning models, what interests many researchers in real-life problems (e.g., fraud detection, credit scoring) is to find hidden patterns in data; particularly when dealing with their challenging imbalanced characteristics. Interpretability is also a key requirement that needs to accompany the used machine learning model. In this concern, often, intrinsically interpretable models are preferred to complex ones, which are in most cases black-box models. Also, linear models are used in some high-risk fields to handle tabular data, even if performance must be sacrificed. In this paper, we introduce Self-Reinforcement Attention (SRA), a novel attention mechanism that provides a relevance of features as a weight vector which is used to learn an intelligible representation. This weight is then used to reinforce or reduce some components of the raw input through element-wise vector multiplication. Our results on synthetic and real-world imbalanced data show that our proposed SRA block is effective in end-to-end combination with baseline models.

翻译：除了机器学习模型的高精度之外，许多研究者在处理现实问题（如欺诈检测、信用评分）时更感兴趣的是发现数据中的隐藏模式，尤其是在处理具有挑战性的不平衡特征时。可解释性也是伴随所用机器学习模型的关键要求。在这方面，通常内在可解释的模型比复杂的模型更受青睐，后者大多是黑箱模型。此外，在一些高风险领域中，即使必须牺牲性能，也会使用线性模型来处理表格数据。本文提出了一种新型注意力机制——自强化注意力（SRA），该机制将特征的相关性作为权重向量，用于学习可理解的表示。随后，通过逐元素向量乘法，该权重被用于增强或削弱原始输入的某些成分。我们在合成和真实世界的不平衡数据上的实验结果表明，所提出的SRA模块在与基线模型进行端到端结合时是有效的。