Decision-making from Partial Instances by Active Feature Querying

Benjamin Quost
Proceedings of the Twelveth International Symposium on Imprecise Probability: Theories and Applications, PMLR 147:264-272, 2021.

Abstract

We consider a classification problem in which test instances are not available as complete feature vectors, but must rather be uncovered by repeated queries to an oracle. We have a limited budget of queries: the problem is then to find the best features to ask the oracle for. We consider here a strategy where features are uncovered one by one, so as to maximize the separation between the classes. Once an instance has been uncovered, the distribution of the remaining instances is updated according to the observation. Experiments on synthetic and real data show that our strategy remains reasonably accurate when a decision must be made based on a limited amount of observed features. We briefly discuss the case of imprecise answers, and list out the many problems arising in this case.

Cite this Paper

BibTeX
@InProceedings{pmlr-v147-quost21a, title = {Decision-making from Partial Instances by Active Feature Querying}, author = {Quost, Benjamin}, booktitle = {Proceedings of the Twelveth International Symposium on Imprecise Probability: Theories and Applications}, pages = {264--272}, year = {2021}, editor = {Cano, Andrés and De Bock, Jasper and Miranda, Enrique and Moral, Serafı́n}, volume = {147}, series = {Proceedings of Machine Learning Research}, month = {06--09 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v147/quost21a/quost21a.pdf}, url = {https://proceedings.mlr.press/v147/quost21a.html}, abstract = {We consider a classification problem in which test instances are not available as complete feature vectors, but must rather be uncovered by repeated queries to an oracle. We have a limited budget of queries: the problem is then to find the best features to ask the oracle for. We consider here a strategy where features are uncovered one by one, so as to maximize the separation between the classes. Once an instance has been uncovered, the distribution of the remaining instances is updated according to the observation. Experiments on synthetic and real data show that our strategy remains reasonably accurate when a decision must be made based on a limited amount of observed features. We briefly discuss the case of imprecise answers, and list out the many problems arising in this case.} }
Endnote
%0 Conference Paper %T Decision-making from Partial Instances by Active Feature Querying %A Benjamin Quost %B Proceedings of the Twelveth International Symposium on Imprecise Probability: Theories and Applications %C Proceedings of Machine Learning Research %D 2021 %E Andrés Cano %E Jasper De Bock %E Enrique Miranda %E Serafı́n Moral %F pmlr-v147-quost21a %I PMLR %P 264--272 %U https://proceedings.mlr.press/v147/quost21a.html %V 147 %X We consider a classification problem in which test instances are not available as complete feature vectors, but must rather be uncovered by repeated queries to an oracle. We have a limited budget of queries: the problem is then to find the best features to ask the oracle for. We consider here a strategy where features are uncovered one by one, so as to maximize the separation between the classes. Once an instance has been uncovered, the distribution of the remaining instances is updated according to the observation. Experiments on synthetic and real data show that our strategy remains reasonably accurate when a decision must be made based on a limited amount of observed features. We briefly discuss the case of imprecise answers, and list out the many problems arising in this case.
APA
Quost, B.. (2021). Decision-making from Partial Instances by Active Feature Querying. Proceedings of the Twelveth International Symposium on Imprecise Probability: Theories and Applications, in Proceedings of Machine Learning Research 147:264-272 Available from https://proceedings.mlr.press/v147/quost21a.html.

Related Material