Intractability and clustering with constraints

Clustering with constraints is a developing area of machine learning. Various papers have used constraints to enforce particular clusterings, seed clustering algorithms and even learn distance functions which are then used for clustering. We present intractability results for some constraint combinations and illustrate both formally and experimentally the implications of these results for using constraints with clustering.

• Type: Conference
• Year: 2007
• Where: ICML
• Authors: Ian Davidson, S. S. Ravi
• Keywords: Constraint Combinations, ICML 2007, Machine Learning