%0 Generic %1 oehmcke2019learning %A Oehmcke, Stefan %A Gieseke, Fabian %D 2019 %K deeplearning masks %T Learning Selection Masks for Deep Neural Networks %U http://arxiv.org/abs/1906.04673 %X Data have often to be moved between servers and clients during the inference phase. For instance, modern virtual assistants collect data on mobile devices and the data are sent to remote servers for the analysis. A related scenario is that clients have to access and download large amounts of data stored on servers in order to apply machine learning models. Depending on the available bandwidth, this data transfer can be a serious bottleneck, which can significantly limit the application machine learning models. In this work, we propose a simple yet effective framework that allows to select certain parts of the input data needed for the subsequent application of a given neural network. Both the masks as well as the neural network are trained simultaneously such that a good model performance is achieved while, at the same time, only a minimal amount of data is selected by the masks. During the inference phase, only the parts selected by the masks have to be transferred between the server and the client. Our experimental evaluation indicates that it is, for certain learning tasks, possible to significantly reduce the amount of data needed to be transferred without affecting the model performance much.

@misc{oehmcke2019learning, abstract = {Data have often to be moved between servers and clients during the inference phase. For instance, modern virtual assistants collect data on mobile devices and the data are sent to remote servers for the analysis. A related scenario is that clients have to access and download large amounts of data stored on servers in order to apply machine learning models. Depending on the available bandwidth, this data transfer can be a serious bottleneck, which can significantly limit the application machine learning models. In this work, we propose a simple yet effective framework that allows to select certain parts of the input data needed for the subsequent application of a given neural network. Both the masks as well as the neural network are trained simultaneously such that a good model performance is achieved while, at the same time, only a minimal amount of data is selected by the masks. During the inference phase, only the parts selected by the masks have to be transferred between the server and the client. Our experimental evaluation indicates that it is, for certain learning tasks, possible to significantly reduce the amount of data needed to be transferred without affecting the model performance much.}, added-at = {2020-02-19T14:23:22.000+0100}, author = {Oehmcke, Stefan and Gieseke, Fabian}, biburl = {https://www.bibsonomy.org/bibtex/28ff9862b89f9d19d6b45e00f792ea9f0/annakrause}, description = {[1906.04673] Learning Selection Masks for Deep Neural Networks}, interhash = {ce56d45762fb8c7fa992343c5136b65e}, intrahash = {8ff9862b89f9d19d6b45e00f792ea9f0}, keywords = {deeplearning masks}, note = {cite arxiv:1906.04673Comment: Submitted to NeurIPS 2019}, timestamp = {2020-02-19T14:23:22.000+0100}, title = {Learning Selection Masks for Deep Neural Networks}, url = {http://arxiv.org/abs/1906.04673}, year = 2019 }