Regularising Non-linear Models Using Feature Side-information

Amina Mollaysa, Pablo Strasser, Alexandros Kalousis
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:2508-2517, 2017.

Abstract

Very often features come with their own vectorial descriptions which provide detailed information about their properties. We refer to these vectorial descriptions as feature side-information. In the standard learning scenario, input is represented as a vector of features and the feature side-information is most often ignored or used only for feature selection prior to model fitting. We believe that feature side-information which carries information about features intrinsic property will help improve model prediction if used in a proper way during learning process. In this paper, we propose a framework that allows for the incorporation of the feature side-information during the learning of very general model families to improve the prediction performance. We control the structures of the learned models so that they reflect features’ similarities as these are defined on the basis of the side-information. We perform experiments on a number of benchmark datasets which show significant predictive performance gains, over a number of baselines, as a result of the exploitation of the side-information.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-mollaysa17a, title = {Regularising Non-linear Models Using Feature Side-information}, author = {Amina Mollaysa and Pablo Strasser and Alexandros Kalousis}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {2508--2517}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/mollaysa17a/mollaysa17a.pdf}, url = {https://proceedings.mlr.press/v70/mollaysa17a.html}, abstract = {Very often features come with their own vectorial descriptions which provide detailed information about their properties. We refer to these vectorial descriptions as feature side-information. In the standard learning scenario, input is represented as a vector of features and the feature side-information is most often ignored or used only for feature selection prior to model fitting. We believe that feature side-information which carries information about features intrinsic property will help improve model prediction if used in a proper way during learning process. In this paper, we propose a framework that allows for the incorporation of the feature side-information during the learning of very general model families to improve the prediction performance. We control the structures of the learned models so that they reflect features’ similarities as these are defined on the basis of the side-information. We perform experiments on a number of benchmark datasets which show significant predictive performance gains, over a number of baselines, as a result of the exploitation of the side-information.} }
Endnote
%0 Conference Paper %T Regularising Non-linear Models Using Feature Side-information %A Amina Mollaysa %A Pablo Strasser %A Alexandros Kalousis %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-mollaysa17a %I PMLR %P 2508--2517 %U https://proceedings.mlr.press/v70/mollaysa17a.html %V 70 %X Very often features come with their own vectorial descriptions which provide detailed information about their properties. We refer to these vectorial descriptions as feature side-information. In the standard learning scenario, input is represented as a vector of features and the feature side-information is most often ignored or used only for feature selection prior to model fitting. We believe that feature side-information which carries information about features intrinsic property will help improve model prediction if used in a proper way during learning process. In this paper, we propose a framework that allows for the incorporation of the feature side-information during the learning of very general model families to improve the prediction performance. We control the structures of the learned models so that they reflect features’ similarities as these are defined on the basis of the side-information. We perform experiments on a number of benchmark datasets which show significant predictive performance gains, over a number of baselines, as a result of the exploitation of the side-information.
APA
Mollaysa, A., Strasser, P. & Kalousis, A.. (2017). Regularising Non-linear Models Using Feature Side-information. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:2508-2517 Available from https://proceedings.mlr.press/v70/mollaysa17a.html.

Related Material