In this paper, we study two challenging problems in explainable AI (XAI) and data clustering. The first is how to directly design a neural network with inherent interpretability, rather than giving post-hoc explanations of a black-box model. The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning. To address these two challenges, we design a novel neural network, which is a differentiable reformulation of the vanilla $k$-means, called inTerpretable nEuraL cLustering (TELL). Our contributions are threefold. First, to the best of our knowledge, most existing XAI works focus on supervised learning paradigms. This work is one of the few XAI studies on unsupervised learning, in particular, data clustering. Second, TELL is an interpretable, or the so-called intrinsically explainable and transparent model. In contrast, most existing XAI studies resort to various means for understanding a black-box model with post-hoc explanations. Third, from the view of data clustering, TELL possesses many properties highly desired by $k$-means, including but not limited to online clustering, plug-and-play module, parallel computing, and provable convergence. Extensive experiments show that our method achieves superior performance comparing with 14 clustering approaches on three challenging data sets. The source code could be accessed at \url{www.pengxi.me}.
翻译:在本文中,我们研究了在可解释的AI(XAI)和数据分组方面的两个具有挑战性的问题。第一个是如何直接设计一个内含可解释性的神经网络,而不是对黑盒模型进行热后解释。第二个是采用不同的神经网络,采用不同的神经网络,包括平行计算、在线集群和集群-有利于代表性学习的优势。为了应对这两个挑战,我们设计了一个新的神经网络,这是对香草 $-k$ 手段的不同重塑,称为Terpreable nEural clustering(TELL) 。我们的贡献有三重。首先,根据我们的知识,大多数现有的XAI工作的重点是监督性学习模式。这项工作是XAI关于非监督性学习,特别是数据组合的少数研究之一。第二,Tell是可解释的,或所谓的内在可解释性可解释和透明的模型。相比之下,大多数现有的 XAI 源研究都采用各种手段来理解黑盒模型,以后HURL CL Clusal commissional 方法, 包括高额和高额分类 模组 。第三,从高额数据分组显示数据分组的高级数据组合,通过高额- cal- cloudal 展示,通过高额- cal 展示,从高额-hal 展示,从高额-hal 展示到高额-hal 方法显示,从高额-hal- cal- cal 和高额-hal 方法显示,从高额- cal 模制的模型显示,从高额的模型到高分解到高分解析制式制。