Online Partitioned Local Depth for semi-supervised applications

TL;DR

This paper presents online PaLD, an extension of the partitioned local depth algorithm, enabling efficient semi-supervised prediction and anomaly detection by updating cohesion networks in real-time.

Contribution

The paper introduces online PaLD, a novel algorithm that efficiently updates cohesion networks for semi-supervised tasks in online settings, improving speed over previous methods.

Findings

Constructs a cohesion network in $O(n^3)$ time.

Extends the network to new data points in $O(n^2)$ time.

Demonstrates applications in online anomaly detection and healthcare classification.

Abstract

We introduce an extension of the partitioned local depth (PaLD) algorithm that is adapted to online applications such as semi-supervised prediction. The new algorithm we present, online PaLD, is well-suited to situations where it is a possible to pre-compute a cohesion network from a reference dataset. After $O(n^3)$ steps to construct a queryable data structure, online PaLD can extend the cohesion network to a new data point in $O(n^2)$ time. Our approach complements previous speed up approaches based on approximation and parallelism. For illustrations, we present applications to online anomaly detection and semi-supervised classification for health-care datasets.