TabNet uses sequential attention with sparsemax masks for instance-wise feature selection and reports state-of-the-art results on several tabular classification and regression benchmarks, plus a masked-reconstruction self-supervised pretraining method.
Learning Structured Sparsity in Deep Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
High demand for computation resources severely hinders deployment of large-scale Deep Neural Networks (DNN) in resource constrained devices. In this work, we propose a Structured Sparsity Learning (SSL) method to regularize the structures (i.e., filters, channels, filter shapes, and layer depth) of DNNs. SSL can: (1) learn a compact structure from a bigger DNN to reduce computation cost; (2) obtain a hardware-friendly structured sparsity of DNN to efficiently accelerate the DNNs evaluation. Experimental results show that SSL achieves on average 5.1x and 3.1x speedups of convolutional layer computation of AlexNet against CPU and GPU, respectively, with off-the-shelf libraries. These speedups are about twice speedups of non-structured sparsity; (3) regularize the DNN structure to improve classification accuracy. The results show that for CIFAR-10, regularization on layer depth can reduce 20 layers of a Deep Residual Network (ResNet) to 18 layers while improve the accuracy from 91.25% to 92.60%, which is still slightly higher than that of original ResNet with 32 layers. For AlexNet, structure regularization by SSL also reduces the error by around ~1%. Open source code is in https://github.com/wenwei202/caffe/tree/scnn
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TabNet: Attentive Interpretable Tabular Learning
TabNet uses sequential attention with sparsemax masks for instance-wise feature selection and reports state-of-the-art results on several tabular classification and regression benchmarks, plus a masked-reconstruction self-supervised pretraining method.