UAI 2021poster5 citations

Exact and approximate hierarchical clustering using A*

Craig S. Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty, Manzil Zaheer, Amr Ahmed, Kyle Cranmer

Abstract

Hierarchical clustering is a critical task in numerous domains. Many approaches are based on heuristics and the properties of the resulting clusterings are studied post hoc. However, in several applications, there is a natural cost function that can be used to characterize the quality of the clustering. In those cases, hierarchical clustering can be seen as a combinatorial optimization problem. To that end, we introduce a new approach based on A* search. We overcome the prohibitively large search space by combining A* with a novel

BibTeX
@InProceedings{pmlr-v161-greenberg21a,
  title = 	 {Exact and approximate hierarchical clustering using A*},
  author =       {Greenberg, Craig S. and Macaluso, Sebastian and Monath, Nicholas and Dubey, Avinava and Flaherty, Patrick and Zaheer, Manzil and Ahmed, Amr and Cranmer, Kyle and McCallum, Andrew},
  booktitle = 	 {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {2061--2071},
  year = 	 {2021},
  editor = 	 {de Campos, Cassio and Maathuis, Marloes H.},
  volume = 	 {161},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {27--30 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v161/greenberg21a/greenberg21a.pdf},
  url = 	 {https://proceedings.mlr.press/v161/greenberg21a.html},
  abstract = 	 {Hierarchical clustering is a critical task in numerous domains. Many approaches are based on heuristics and the properties of the resulting clusterings are studied post hoc. However, in several applications, there is a natural cost function that can be used to characterize the quality of the clustering. In those cases, hierarchical clustering can be seen as a combinatorial optimization problem. To that end, we introduce a new approach based on A* search. We overcome the prohibitively large search space by combining A* with a novel