Decorrelating Adversarial Nets for Clustering Mobile Network Data

TL;DR

This paper introduces DANCE, a novel deep clustering algorithm designed to effectively analyze mobile network data by separating relevant features, outperforming existing methods in network automation tasks.

Contribution

The paper presents DANCE, a new deep clustering approach that enhances clustering performance on mobile network data by disentangling relevant and irrelevant features.

Findings

DANCE outperforms existing deep clustering algorithms on mobile network datasets.

Separating clustering-relevant features improves clustering consistency and accuracy.

DANCE is suitable for network automation use-cases with complex data.

Abstract

Deep learning will play a crucial role in enabling cognitive automation for the mobile networks of the future. Deep clustering, a subset of deep learning, could be a valuable tool for many network automation use-cases. Unfortunately, most state-of-the-art clustering algorithms target image datasets, which makes them hard to apply to mobile network data due to their highly tuned nature and related assumptions about the data. In this paper, we propose a new algorithm, DANCE (Decorrelating Adversarial Nets for Clustering-friendly Encoding), intended to be a reliable deep clustering method which also performs well when applied to network automation use-cases. DANCE uses a reconstructive clustering approach, separating clustering-relevant from clustering-irrelevant features in a latent representation. This separation removes unnecessary information from the clustering, increasing consistency and peak performance. We comprehensively evaluate DANCE and other select state-of-the-art deep clustering algorithms, and show that DANCE outperforms these algorithms by a significant margin on a mobile network dataset.