Semi-Supervised Clustering with Neural Networks

TL;DR

This paper introduces ClusterNet, a semi-supervised neural network that effectively combines limited labeled data with abundant unlabeled data for improved clustering performance.

Contribution

It proposes a novel loss function and framework that leverage very few labeled samples alongside unlabeled data for deep clustering.

Findings

Outperforms existing deep clustering methods on multiple datasets.

Effectively utilizes less than 5% labeled data.

Learns meaningful latent representations and cluster centers.

Abstract

Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their dependence on large set of labeled data samples. In this paper, we propose ClusterNet that uses pairwise semantic constraints from very few labeled data samples (<5% of total data) and exploits the abundant unlabeled data to drive the clustering approach. We define a new loss function that uses pairwise semantic similarity between objects combined with constrained k-means clustering to efficiently utilize both labeled and unlabeled data in the same framework. The proposed network uses convolution autoencoder to learn a latent representation that groups data into k specified clusters, while also learning the cluster centers simultaneously. We evaluate and compare the performance of ClusterNet on several datasets and state of the art deep clustering approaches.