Multi-Dimensional Classification via Sparse Label Encoding

Bin-Bin Jia, Min-Ling Zhang
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4917-4926, 2021.

Abstract

In multi-dimensional classification (MDC), there are multiple class variables in the output space with each of them corresponding to one heterogeneous class space. Due to the heterogeneity of class spaces, it is quite challenging to consider the dependencies among class variables when learning from MDC examples. In this paper, we propose a novel MDC approach named SLEM which learns the predictive model in an encoded label space instead of the original heterogeneous one. Specifically, SLEM works in an encoding-training-decoding framework. In the encoding phase, each class vector is mapped into a real-valued one via three cascaded operations including pairwise grouping, one-hot conversion and sparse linear encoding. In the training phase, a multi-output regression model is learned within the encoded label space. In the decoding phase, the predicted class vector is obtained by adapting orthogonal matching pursuit over outputs of the learned multi-output regression model. Experimental results clearly validate the superiority of SLEM against state-of-the-art MDC approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-jia21c, title = {Multi-Dimensional Classification via Sparse Label Encoding}, author = {Jia, Bin-Bin and Zhang, Min-Ling}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {4917--4926}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/jia21c/jia21c.pdf}, url = {https://proceedings.mlr.press/v139/jia21c.html}, abstract = {In multi-dimensional classification (MDC), there are multiple class variables in the output space with each of them corresponding to one heterogeneous class space. Due to the heterogeneity of class spaces, it is quite challenging to consider the dependencies among class variables when learning from MDC examples. In this paper, we propose a novel MDC approach named SLEM which learns the predictive model in an encoded label space instead of the original heterogeneous one. Specifically, SLEM works in an encoding-training-decoding framework. In the encoding phase, each class vector is mapped into a real-valued one via three cascaded operations including pairwise grouping, one-hot conversion and sparse linear encoding. In the training phase, a multi-output regression model is learned within the encoded label space. In the decoding phase, the predicted class vector is obtained by adapting orthogonal matching pursuit over outputs of the learned multi-output regression model. Experimental results clearly validate the superiority of SLEM against state-of-the-art MDC approaches.} }
Endnote
%0 Conference Paper %T Multi-Dimensional Classification via Sparse Label Encoding %A Bin-Bin Jia %A Min-Ling Zhang %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-jia21c %I PMLR %P 4917--4926 %U https://proceedings.mlr.press/v139/jia21c.html %V 139 %X In multi-dimensional classification (MDC), there are multiple class variables in the output space with each of them corresponding to one heterogeneous class space. Due to the heterogeneity of class spaces, it is quite challenging to consider the dependencies among class variables when learning from MDC examples. In this paper, we propose a novel MDC approach named SLEM which learns the predictive model in an encoded label space instead of the original heterogeneous one. Specifically, SLEM works in an encoding-training-decoding framework. In the encoding phase, each class vector is mapped into a real-valued one via three cascaded operations including pairwise grouping, one-hot conversion and sparse linear encoding. In the training phase, a multi-output regression model is learned within the encoded label space. In the decoding phase, the predicted class vector is obtained by adapting orthogonal matching pursuit over outputs of the learned multi-output regression model. Experimental results clearly validate the superiority of SLEM against state-of-the-art MDC approaches.
APA
Jia, B. & Zhang, M.. (2021). Multi-Dimensional Classification via Sparse Label Encoding. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:4917-4926 Available from https://proceedings.mlr.press/v139/jia21c.html.

Related Material