Generalized Clustering by Learning to Optimize Expected Normalized Cuts

10/16/2019
by   Azade Nazi, et al.
0

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 generalization results are superior (by up to 21.9 top-performing clustering approach with the ability to generalize.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2021

Cluster Analysis with Deep Embeddings and Contrastive Learning

Unsupervised disentangled representation learning is a long-standing pro...
research
12/29/2022

Constant Approximation for Normalized Modularity and Associations Clustering

We study the problem of graph clustering under a broad class of objectiv...
research
12/05/2019

Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

The clustering of unlabeled raw images is a daunting task, which has rec...
research
01/31/2023

Domain-Generalizable Multiple-Domain Clustering

Accurately clustering high-dimensional measurements is vital for adequat...
research
10/30/2019

Meta-Learning to Cluster

Clustering is one of the most fundamental and wide-spread techniques in ...
research
07/17/2018

Invariant Information Distillation for Unsupervised Image Segmentation and Clustering

We present a new method that learns to segment and cluster images withou...
research
06/28/2018

A probabilistic constrained clustering for transfer learning and image category discovery

Neural network-based clustering has recently gained popularity, and in p...

Please sign up or login with your details

Forgot password? Click here to reset