Interactive Bayesian Hierarchical Clustering

Sharad Vikram, Sanjoy Dasgupta
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2081-2090, 2016.

Abstract

Clustering is a powerful tool in data analysis, but it is often difficult to find a grouping that aligns with a user’s needs. To address this, several methods incorporate constraints obtained from users into clustering algorithms, but unfortunately do not apply to hierarchical clustering. We design an interactive Bayesian algorithm that incorporates user interaction into hierarchical clustering while still utilizing the geometry of the data by sampling a constrained posterior distribution over hierarchies. We also suggest several ways to intelligently query a user. The algorithm, along with the querying schemes, shows promising results on real data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v48-vikram16, title = {Interactive Bayesian Hierarchical Clustering}, author = {Vikram, Sharad and Dasgupta, Sanjoy}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2081--2090}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/vikram16.pdf}, url = {https://proceedings.mlr.press/v48/vikram16.html}, abstract = {Clustering is a powerful tool in data analysis, but it is often difficult to find a grouping that aligns with a user’s needs. To address this, several methods incorporate constraints obtained from users into clustering algorithms, but unfortunately do not apply to hierarchical clustering. We design an interactive Bayesian algorithm that incorporates user interaction into hierarchical clustering while still utilizing the geometry of the data by sampling a constrained posterior distribution over hierarchies. We also suggest several ways to intelligently query a user. The algorithm, along with the querying schemes, shows promising results on real data.} }
Endnote
%0 Conference Paper %T Interactive Bayesian Hierarchical Clustering %A Sharad Vikram %A Sanjoy Dasgupta %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-vikram16 %I PMLR %P 2081--2090 %U https://proceedings.mlr.press/v48/vikram16.html %V 48 %X Clustering is a powerful tool in data analysis, but it is often difficult to find a grouping that aligns with a user’s needs. To address this, several methods incorporate constraints obtained from users into clustering algorithms, but unfortunately do not apply to hierarchical clustering. We design an interactive Bayesian algorithm that incorporates user interaction into hierarchical clustering while still utilizing the geometry of the data by sampling a constrained posterior distribution over hierarchies. We also suggest several ways to intelligently query a user. The algorithm, along with the querying schemes, shows promising results on real data.
RIS
TY - CPAPER TI - Interactive Bayesian Hierarchical Clustering AU - Sharad Vikram AU - Sanjoy Dasgupta BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-vikram16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2081 EP - 2090 L1 - http://proceedings.mlr.press/v48/vikram16.pdf UR - https://proceedings.mlr.press/v48/vikram16.html AB - Clustering is a powerful tool in data analysis, but it is often difficult to find a grouping that aligns with a user’s needs. To address this, several methods incorporate constraints obtained from users into clustering algorithms, but unfortunately do not apply to hierarchical clustering. We design an interactive Bayesian algorithm that incorporates user interaction into hierarchical clustering while still utilizing the geometry of the data by sampling a constrained posterior distribution over hierarchies. We also suggest several ways to intelligently query a user. The algorithm, along with the querying schemes, shows promising results on real data. ER -
APA
Vikram, S. & Dasgupta, S.. (2016). Interactive Bayesian Hierarchical Clustering. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2081-2090 Available from https://proceedings.mlr.press/v48/vikram16.html.

Related Material