Recursive Partitional Clustering Algorithm

A Recursive Partitional Clustering Algorithm is a hierarchical clustering algorithm that is a top-down algorithm which partitions all of the data records immediately and then iteratively adjust them.

• AKA: Top-Down Hierarchical Clustering, Recursive Partitioning.
• Context:
  • It can (typically) involve a Cluster Partition Operation.
  • It can be applied by a Partitional Clustering System.
  • It can range from being a Hard-Clusters Partitional Clustering Algorithm (e.g. partitional hierarchical clustering) to being a Soft-Clusters Partitional Clustering Algorithm.
• Example(s):
  • A k-Means Clustering Algorithm, such as bisecting k-means.
  • A k-Medoid Clustering Algorithm.
  • …
• Counter-Example(s):
  • Bottom-Up Hierarchical Clustering Algorithm/Agglomerative Clustering Algorithm.
  • Top-Down Soft-Clusters Clustering Algorithm.
• See: Hierarchical Clustering Task, Set Partition, Equivalence Relation.

---

---

References

2009

• http://nlp.stanford.edu/IR-book/html/htmledition/hierarchical-agglomerative-clustering-1.html
  • QUOTE: Hierarchical clustering algorithms are either top-down or bottom-up. … HAC is more frequently used in IR than top-down clustering ...

• (Wikipedia, 2009) ⇒ http://en.wikipedia.org/wiki/Cluster_analysis#Hierarchical_clustering
  • Hierarchical clustering builds (agglomerative), or breaks up (divisive), a hierarchy of clusters. The traditional representation of this hierarchy is a tree (called a dendrogram), with individual elements at one end and a single cluster containing every element at the other. …

    … Cutting the tree at a given height will give a clustering at a selected precision. In the following example, cutting after the second row will yield clusters {a} {b c} {d e} {f}. Cutting after the third row will yield clusters {a} {b c} {d e f}, which is a coarser clustering, with a smaller number of larger clusters.

• http://www.nature.com/nrg/journal/v5/n6/glossary/nrg1349_glossary.html
  • An unsupervised clustering technique. Each data point initially forms a separate cluster and then clusters are merged sequentially based on ...

• http://nlp.stanford.edu/IR-book/html/htmledition/hierarchical-agglomerative-clustering-1.html
  • QUOTE: … Top-down clustering requires a method for splitting a cluster. It proceeds by splitting clusters recursively until individual documents are reached.

2003

• http://www.nature.com/nrg/journal/v4/n9/glossary/nrg1155_glossary.html
  • RECURSIVE PARTITIONING A process for identifying complex relationships in large sets by dividing them into a hierarchy of smaller and more homogeneous subgroups on the basis of the most statistically significant indicators.

---