Clustering Partial Lexicographic Preference Trees

Clustering Partial Lexicographic Preference Trees. Allen*, J., Liu, X., Reddivari, S., & Umapathy, K. In Proceedings of the 33rd International Florida Artificial Intelligence Research Society Conference (FLAIRS), 2020. AAAI Press.

Paper

Clustering Partial Lexicographic Preference Trees [pdf]

Paper abstract bibtex 12 downloads

In this work, we consider the problem of clustering partial lexicographic preference trees (PLP-trees), intuitive and often compact representations of user preferences over multi-valued attributes. Due to the preordering nature of PLP-trees, we define a variant of Kendall’s τ distance metric to be used to compute distances between PLP-trees for clustering. To this end, extending the previous work by Li and Kazimipour (Li and Kazimipour 2018), we propose a polynomial time algorithm PlpDis to compute such distances, and present empirical results comparing it against the brute-force baseline. Based on PlpDis, we use various distance-based clustering methods to cluster PLP-trees learned from a car evaluation dataset. Our experiments show that hierarchical agglomerative nesting (AGNES) is the best choice for clustering PLP-trees, and that the single-linkage variant of AGNES is the best fit for clustering large numbers of trees.

@inproceedings{conf/flairs33/AllenLRU,
  author = {Joseph Allen* and Xudong Liu and Sandeep Reddivari and Karthikeyan Umapathy},
  booktitle = {Proceedings of the 33rd International Florida Artificial Intelligence Research Society Conference (FLAIRS)},
  publisher = {AAAI Press},
  title = {Clustering Partial Lexicographic Preference Trees},
  abstract = {In this work, we consider the problem of clustering partial lexicographic preference trees (PLP-trees), intuitive and often compact representations of user preferences over multi-valued attributes. Due to the preordering nature of PLP-trees, we define a variant of Kendall’s τ distance metric to be used to compute distances between PLP-trees for clustering. To this end, extending the previous work by Li and Kazimipour (Li and Kazimipour 2018), we propose a polynomial time algorithm PlpDis to compute such distances, and present empirical results comparing it against the brute-force baseline. Based on PlpDis, we use various distance-based clustering methods to cluster PLP-trees learned from a car evaluation dataset. Our experiments show that hierarchical agglomerative nesting (AGNES) is the best choice for clustering PLP-trees, and that the single-linkage variant of AGNES is the best fit for clustering large numbers of trees.},
	url="https://aaai.org/ocs/index.php/FLAIRS/FLAIRS20/paper/view/18425",
  url_Paper = {http://xudongliu.domains.unf.edu/resources/PLPClustering_flairs20.pdf},
  year = 2020
}

Downloads: 12