Feature Convolutional Networks

He Hu
Proceedings of The 13th Asian Conference on Machine Learning, PMLR 157:830-839, 2021.

Abstract

Convolutional neural networks are among the most successful deep learning models used for image processing, computer vision and natural language processing applications. In this paper, we define convolution operator for numerical tabular features and thus propose feature convolutional network model for machine learning tasks. Feature convolutional networks contain feature convolution layer to extract pairwise feature convolutions in the relational feature spaces. Compared with the baseline multi-layer neural network model, the feature convolutional network gains better performance among all the experiments. The experiments results suggest that feature convolutional networks can generate efficient features automatically and provide better performance through automatic feature learning. The demo code is at https://github.com/info-ruc/FeatConvNet.

Cite this Paper

BibTeX
@InProceedings{pmlr-v157-hu21a, title = {Feature Convolutional Networks}, author = {Hu, He}, booktitle = {Proceedings of The 13th Asian Conference on Machine Learning}, pages = {830--839}, year = {2021}, editor = {Balasubramanian, Vineeth N. and Tsang, Ivor}, volume = {157}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v157/hu21a/hu21a.pdf}, url = {https://proceedings.mlr.press/v157/hu21a.html}, abstract = {Convolutional neural networks are among the most successful deep learning models used for image processing, computer vision and natural language processing applications. In this paper, we define convolution operator for numerical tabular features and thus propose feature convolutional network model for machine learning tasks. Feature convolutional networks contain feature convolution layer to extract pairwise feature convolutions in the relational feature spaces. Compared with the baseline multi-layer neural network model, the feature convolutional network gains better performance among all the experiments. The experiments results suggest that feature convolutional networks can generate efficient features automatically and provide better performance through automatic feature learning. The demo code is at https://github.com/info-ruc/FeatConvNet.} }
Endnote
%0 Conference Paper %T Feature Convolutional Networks %A He Hu %B Proceedings of The 13th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Vineeth N. Balasubramanian %E Ivor Tsang %F pmlr-v157-hu21a %I PMLR %P 830--839 %U https://proceedings.mlr.press/v157/hu21a.html %V 157 %X Convolutional neural networks are among the most successful deep learning models used for image processing, computer vision and natural language processing applications. In this paper, we define convolution operator for numerical tabular features and thus propose feature convolutional network model for machine learning tasks. Feature convolutional networks contain feature convolution layer to extract pairwise feature convolutions in the relational feature spaces. Compared with the baseline multi-layer neural network model, the feature convolutional network gains better performance among all the experiments. The experiments results suggest that feature convolutional networks can generate efficient features automatically and provide better performance through automatic feature learning. The demo code is at https://github.com/info-ruc/FeatConvNet.
APA
Hu, H.. (2021). Feature Convolutional Networks. Proceedings of The 13th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 157:830-839 Available from https://proceedings.mlr.press/v157/hu21a.html.

Related Material