# XAI Beyond Classification: Interpretable Neural Clustering

arXiv: https://arxiv.org/abs/1808.07292 · HTML: https://mlsanity.com/paper/1808.07292/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2018.

## Built on by (most cited first, 24 of 24)

- [Twin Contrastive Learning for Online Clustering](https://mlsanity.com/paper/2210.11680/) (2022)
- [Deep Multiview Clustering by Contrasting Cluster Assignments](https://mlsanity.com/paper/2304.10769/) (2023)
- [A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?](https://mlsanity.com/paper/2304.04780/) (2023)
- [Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios](https://mlsanity.com/paper/2303.17245/) (2023)
- [Interpretable Deep Clustering for Tabular Data](https://mlsanity.com/paper/2306.04785/) (2023)
- [Self-supervised Contrastive Attributed Graph Clustering](https://mlsanity.com/paper/2110.08264/) (2021)
- [Local Sample-weighted Multiple Kernel Clustering with Consensus Discriminative Graph](https://mlsanity.com/paper/2207.02846/) (2022)
- [Incomplete Multi-view Clustering via Cross-view Relation Transfer](https://mlsanity.com/paper/2112.00739/) (2021)
- [Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation](https://mlsanity.com/paper/2205.10481/) (2022)
- [OpenViewer: Openness-Aware Multi-View Learning](https://mlsanity.com/paper/2412.12596/) (2024)
- [Unsupervised Deep Discriminant Analysis Based Clustering](https://mlsanity.com/paper/2206.04686/) (2022)
- [Hate Speech Detection via Dual Contrastive Learning](https://mlsanity.com/paper/2307.05578/) (2023)
- [NeurCAM: Interpretable Neural Clustering via Additive Models](https://mlsanity.com/paper/2408.13361/) (2024)
- [Wasserstein-Aligned Hyperbolic Multi-View Clustering](https://mlsanity.com/paper/2512.09402/) (2025)
- [Deep Embedding Clustering Driven by Sample Stability](https://mlsanity.com/paper/2401.15989/) (2024)
- [AcME-AD: Accelerated Model Explanations for Anomaly Detection](https://mlsanity.com/paper/2403.01245/) (2024)
- [Recent Trends in Artificial Intelligence Technology: A Scoping Review](https://mlsanity.com/paper/2305.04532/) (2023)
- [Cross-View Graph Consistency Learning for Invariant Graph Representations](https://mlsanity.com/paper/2311.11821/) (2023)
- [Explainable Learning with Gaussian Processes](https://mlsanity.com/paper/2403.07072/) (2024)
- [GCC: Generative Calibration Clustering](https://mlsanity.com/paper/2404.09115/) (2024)
- [Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection](https://mlsanity.com/paper/2407.11979/) (2024)
- [Anisotropic, Sparse and Interpretable Physics-Informed Neural Networks for PDEs](https://mlsanity.com/paper/2207.00377/) (2022)
- [Weight-Informed Self-Explaining Clustering for Mixed-Type Tabular Data](https://mlsanity.com/paper/2604.05857/) (2026)
- [Cohort Organized Learning: Clustering Through Agreement](https://mlsanity.com/paper/2606.21743/) (2026)

## Abstract (arXiv)

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 urlwww.pengxi.me.