Learned Accelerator Framework for Angular-Distance-Based High-Dimensional DBSCAN

TL;DR

This paper introduces LAF, a learned accelerator framework that significantly improves the efficiency and quality of high-dimensional DBSCAN clustering using angular distance, by predicting core points and correcting false negatives.

Contribution

The paper presents a novel learned framework with a cardinality estimator and post-processing to accelerate high-dimensional DBSCAN clustering, addressing performance issues in high-dimensional spaces.

Findings

LAF outperforms state-of-the-art DBSCAN variants in efficiency.

LAF improves clustering quality in high-dimensional data.

The framework effectively reduces unnecessary computations.

Abstract

Density-based clustering is a commonly used tool in data science. Today many data science works are utilizing high-dimensional neural embeddings. However, traditional density-based clustering techniques like DBSCAN have a degraded performance on high-dimensional data. In this paper, we propose LAF, a generic learned accelerator framework to speed up the original DBSCAN and the sampling-based variants of DBSCAN on high-dimensional data with angular distance metric. This framework consists of a learned cardinality estimator and a post-processing module. The cardinality estimator can fast predict whether a data point is core or not to skip unnecessary range queries, while the post-processing module detects the false negative predictions and merges the falsely separated clusters. The evaluation shows our LAF-enhanced DBSCAN method outperforms the state-of-the-art efficient DBSCAN variants on both efficiency and quality.