Automatic depth-based local center clustering via $β$-integrated local depth and adaptive grouping
A new unsupervised clustering method, A-DLCC, estimates cluster count automatically without numerical parameter tuning.
Researchers propose automatic depth-based local center clustering (A-DLCC), an unsupervised method that avoids user-specified cluster counts and neighborhood sizes. It ranks stable exemplars with beta-integrated local depth and merges groups using a nonparametric similarity measure plus a bottleneck-path criterion checked against a configuration-model null. Experiments on synthetic and real data show the rule estimates the number of clusters and stops merging without numerical parameter tuning.
- A-DLCC clusters data without a preset cluster count or neighborhood size.
- Local centers are found with beta-integrated local depth.
- An adaptive merge rule estimates cluster count and when to stop.
- Synthetic and real-data tests require no numerical parameter tuning.
From the original article
1 min read at arxiv.orgClustering is an unsupervised learning technique that partitions unlabeled data into groups. Most existing methods require user-specified parameters, such as the number of clusters or neighborhood size. Conversely, we propose automatic depth-based local center clustering (A-DLCC), a fully data-driven method that eliminates numerical parameter tuning.
By Siyi Wang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.