Class Proportion Estimation with Application to Multiclass Anomaly Rejection

Tyler Sanderson, Clayton Scott
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:850-858, 2014.

Abstract

This work addresses two classification problems that fall under the heading of domain adaptation, wherein the distributions of training and testing examples differ. The first problem studied is that of class proportion estimation, which is the problem of estimating the class proportions in an unlabeled testing data set given labeled examples of each class. Compared to previous work on this problem, our approach has the novel feature that it does not require labeled training data from one of the classes. This property allows us to address the second domain adaptation problem, namely, multiclass anomaly rejection. Here, the goal is to design a classifier that has the option of assigning a “reject” label, indicating that the instance did not arise from a class present in the training data. We establish consistent learning strategies for both of these domain adaptation problems, which to our knowledge are the first of their kind. We also implement the class proportion estimation technique and demonstrate its performance on several benchmark data sets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v33-sanderson14, title = {{Class Proportion Estimation with Application to Multiclass Anomaly Rejection}}, author = {Sanderson, Tyler and Scott, Clayton}, booktitle = {Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics}, pages = {850--858}, year = {2014}, editor = {Kaski, Samuel and Corander, Jukka}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/sanderson14.pdf}, url = {https://proceedings.mlr.press/v33/sanderson14.html}, abstract = {This work addresses two classification problems that fall under the heading of domain adaptation, wherein the distributions of training and testing examples differ. The first problem studied is that of class proportion estimation, which is the problem of estimating the class proportions in an unlabeled testing data set given labeled examples of each class. Compared to previous work on this problem, our approach has the novel feature that it does not require labeled training data from one of the classes. This property allows us to address the second domain adaptation problem, namely, multiclass anomaly rejection. Here, the goal is to design a classifier that has the option of assigning a “reject” label, indicating that the instance did not arise from a class present in the training data. We establish consistent learning strategies for both of these domain adaptation problems, which to our knowledge are the first of their kind. We also implement the class proportion estimation technique and demonstrate its performance on several benchmark data sets.} }
Endnote
%0 Conference Paper %T Class Proportion Estimation with Application to Multiclass Anomaly Rejection %A Tyler Sanderson %A Clayton Scott %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-sanderson14 %I PMLR %P 850--858 %U https://proceedings.mlr.press/v33/sanderson14.html %V 33 %X This work addresses two classification problems that fall under the heading of domain adaptation, wherein the distributions of training and testing examples differ. The first problem studied is that of class proportion estimation, which is the problem of estimating the class proportions in an unlabeled testing data set given labeled examples of each class. Compared to previous work on this problem, our approach has the novel feature that it does not require labeled training data from one of the classes. This property allows us to address the second domain adaptation problem, namely, multiclass anomaly rejection. Here, the goal is to design a classifier that has the option of assigning a “reject” label, indicating that the instance did not arise from a class present in the training data. We establish consistent learning strategies for both of these domain adaptation problems, which to our knowledge are the first of their kind. We also implement the class proportion estimation technique and demonstrate its performance on several benchmark data sets.
RIS
TY - CPAPER TI - Class Proportion Estimation with Application to Multiclass Anomaly Rejection AU - Tyler Sanderson AU - Clayton Scott BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-sanderson14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 33 SP - 850 EP - 858 L1 - http://proceedings.mlr.press/v33/sanderson14.pdf UR - https://proceedings.mlr.press/v33/sanderson14.html AB - This work addresses two classification problems that fall under the heading of domain adaptation, wherein the distributions of training and testing examples differ. The first problem studied is that of class proportion estimation, which is the problem of estimating the class proportions in an unlabeled testing data set given labeled examples of each class. Compared to previous work on this problem, our approach has the novel feature that it does not require labeled training data from one of the classes. This property allows us to address the second domain adaptation problem, namely, multiclass anomaly rejection. Here, the goal is to design a classifier that has the option of assigning a “reject” label, indicating that the instance did not arise from a class present in the training data. We establish consistent learning strategies for both of these domain adaptation problems, which to our knowledge are the first of their kind. We also implement the class proportion estimation technique and demonstrate its performance on several benchmark data sets. ER -
APA
Sanderson, T. & Scott, C.. (2014). Class Proportion Estimation with Application to Multiclass Anomaly Rejection. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 33:850-858 Available from https://proceedings.mlr.press/v33/sanderson14.html.

Related Material