A Self-Organizing Clustering System for Unsupervised Distribution Shift Detection

TL;DR

This paper introduces a novel self-organizing clustering framework for detecting distribution shifts in non-stationary data, leveraging bio-inspired topological maps and Gaussian comparison methods for robustness and speed.

Contribution

It proposes a new continual learning approach using self-organizing maps and statistical analysis to detect distribution changes in both supervised and unsupervised settings.

Findings

Effective detection of distribution shifts in image, sensor, and environmental data.

Outperforms PCA and Kernel-PCA in robustness and speed.

Applicable in real-world non-stationary data scenarios.

Abstract

Modeling non-stationary data is a challenging problem in the field of continual learning, and data distribution shifts may result in negative consequences on the performance of a machine learning model. Classic learning tools are often vulnerable to perturbations of the input covariates, and are sensitive to outliers and noise, and some tools are based on rigid algebraic assumptions. Distribution shifts are frequently occurring due to changes in raw materials for production, seasonality, a different user base, or even adversarial attacks. Therefore, there is a need for more effective distribution shift detection techniques. In this work, we propose a continual learning framework for monitoring and detecting distribution changes. We explore the problem in a latent space generated by a bio-inspired self-organizing clustering and statistical aspects of the latent space. In particular, we investigate the projections made by two topology-preserving maps: the Self-Organizing Map and the Scale Invariant Map. Our method can be applied in both a supervised and an unsupervised context. We construct the assessment of changes in the data distribution as a comparison of Gaussian signals, making the proposed method fast and robust. We compare it to other unsupervised techniques, specifically Principal Component Analysis (PCA) and Kernel-PCA. Our comparison involves conducting experiments using sequences of images (based on MNIST and injected shifts with adversarial samples), chemical sensor measurements, and the environmental variable related to ozone levels. The empirical study reveals the potential of the proposed approach.