Adaptive Network Sparsification via Dependent Variational Beta-Bernoulli Dropout

by   Juho Lee, et al.

While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such input-independent dropout, each neuron is evolved to be generic across inputs, which makes it difficult to sparsify networks without accuracy loss. To overcome this limitation, we propose adaptive variational dropout whose probabilities are drawn from sparsity-inducing beta-Bernoulli prior. It allows each neuron to be evolved either to be generic or specific for certain inputs, or dropped altogether. Such input-adaptive sparsity- inducing dropout allows the resulting network to tolerate larger degree of sparsity without losing its expressive power by removing redundancies among features. We validate our dependent variational beta-Bernoulli dropout on multiple public datasets, on which it obtains significantly more compact networks than baseline methods, with consistent accuracy improvements over the base networks.


page 1

page 2

page 3

page 4


Variational Dropout via Empirical Bayes

We study the Automatic Relevance Determination procedure applied to deep...

Compacting Neural Network Classifiers via Dropout Training

We introduce dropout compaction, a novel method for training feed-forwar...

DropMax: Adaptive Stochastic Softmax

We propose DropMax, a stochastic version of softmax classifier which at ...

Contextual Dropout: An Efficient Sample-Dependent Dropout Module

Dropout has been demonstrated as a simple and effective module to not on...

Dropout Prediction Variation Estimation Using Neuron Activation Strength

It is well-known DNNs would generate different prediction results even g...

Please sign up or login with your details

Forgot password? Click here to reset