Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders

TL;DR

This paper introduces an interpretable anomaly detection method for cellular networks using variational autoencoders that learn meaningful latent representations of KPIs, enabling faster and more autonomous detection.

Contribution

The paper proposes a novel VAE-based framework that enhances interpretability of anomalies in cellular network KPIs through learned latent representations and centroid-based explanations.

Findings

Effective detection of anomalies via reconstruction loss and Z-scores

Enhanced interpretability through centroid-based representation learning

Faster, autonomous anomaly detection in large-scale cellular data

Abstract

This paper addresses the challenges of detecting anomalies in cellular networks in an interpretable way and proposes a new approach using variational autoencoders (VAEs) that learn interpretable representations of the latent space for each Key Performance Indicator (KPI) in the dataset. This enables the detection of anomalies based on reconstruction loss and Z-scores. We ensure the interpretability of the anomalies via additional information centroids (c) using the K-means algorithm to enhance representation learning. We evaluate the performance of the model by analyzing patterns in the latent dimension for specific KPIs and thereby demonstrate the interpretability and anomalies. The proposed framework offers a faster and autonomous solution for detecting anomalies in cellular networks and showcases the potential of deep learning-based algorithms in handling big data.