Deep Goal-Oriented Clustering

TL;DR

This paper introduces Deep Goal-Oriented Clustering (DGC), a probabilistic framework that jointly leverages supervision and data structure to improve clustering and prediction tasks simultaneously.

Contribution

It presents a novel end-to-end probabilistic model that integrates supervised side-information with unsupervised data modeling for improved clustering and prediction.

Findings

Achieves prediction accuracy comparable to state-of-the-art methods.

Simultaneously learns meaningful clustering strategies.

Demonstrates effectiveness across various datasets.

Abstract

Clustering and prediction are two primary tasks in the fields of unsupervised and supervised learning, respectively. Although much of the recent advances in machine learning have been centered around those two tasks, the interdependent, mutually beneficial relationship between them is rarely explored. One could reasonably expect appropriately clustering the data would aid the downstream prediction task and, conversely, a better prediction performance for the downstream task could potentially inform a more appropriate clustering strategy. In this work, we focus on the latter part of this mutually beneficial relationship. To this end, we introduce Deep Goal-Oriented Clustering (DGC), a probabilistic framework that clusters the data by jointly using supervision via side-information and unsupervised modeling of the inherent data structure in an end-to-end fashion. We show the effectiveness of our model on a range of datasets by achieving prediction accuracies comparable to the state-of-the-art, while, more importantly in our setting, simultaneously learning congruent clustering strategies.