# Generalized Clustering by Learning to Optimize Expected Normalized Cuts

arXiv: https://arxiv.org/abs/1910.07623 · HTML: https://mlsanity.com/paper/1910.07623/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2019.

## Built on by (most cited first, 3 of 3)

- [Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods](https://mlsanity.com/paper/2205.11508/) (2022)
- [Deep Clustering with a Constraint for Topological Invariance based on Symmetric InfoNCE](https://mlsanity.com/paper/2303.03036/) (2023)
- [Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering](https://mlsanity.com/paper/2503.09260/) (2025)

## Abstract (arXiv)

We introduce a novel end-to-end approach for learning to cluster in the absence of labeled examples. Our clustering objective is based on optimizing normalized cuts, a criterion which measures both intra-cluster similarity as well as inter-cluster dissimilarity. We define a differentiable loss function equivalent to the expected normalized cuts. Unlike much of the work in unsupervised deep learning, our trained model directly outputs final cluster assignments, rather than embeddings that need further processing to be usable. Our approach generalizes to unseen datasets across a wide variety of domains, including text, and image. Specifically, we achieve state-of-the-art results on popular unsupervised clustering benchmarks (e.g., MNIST, Reuters, CIFAR-10, and CIFAR-100), outperforming the strongest baselines by up to 10.9%. Our generalization results are superior (by up to 21.9%) to the recent top-performing clustering approach with the ability to generalize.