Sublinear Clustering Task

A Sublinear Clustering Task is a Clustering Task that only uses a small subset of the input data.

• Context:
  • It usually uses a subset that has been randomly selected.
  • It can be solved by Sublinear Clustering System that implements Sublinear Clustering Algorithms.
• Example(s):
  • the task described in Czumaj & Sohler (2017),
  • ...
  • …
• Counter-Example(s)
  • Correlation Clustering Task,
  • Evolutionary Clustering Task,
  • Model-Based Clustering Task,
  • Categorical Data Clustering Task,
  • Cluster Editing Task,
  • Density-Based Clustering Task.
• See: Cluster Ensemble, Consensus Clustering, Random Process, Unsupervised Classification Task.

---

---

References

2017

• (Czumaj & Sohler, 2017) ⇒ Artur Czumaj, and Christian Sohler. (2017). "Sublinear Clustering". In: (Sammut & Webb, 2017). DOI:10.1007/978-1-4899-7687-1_798
  • QUOTE: Sublinear clustering describes the process of clustering a given set of input objects using only a small subset of the input set, which is typically selected by a random process. A solution computed by a sublinear clustering algorithm is an implicit description of the clustering (rather than a partition of the input objects), for example in the form of cluster centers. Sublinear clustering is usually applied when the input set is too large to be processed with standard clustering algorithms.

---