Ensemble-Compression: A New Method for Parallel Training of Deep Neural Networks

By Shizhao Sun, Wei Chen, Jiang Bian, Xiaoguang Liu, Tie-Yan Liu. 2016

30 citations recorded by the source corpus.

Parallelization framework has become a necessity to speed up the training of deep neural networks (DNN) recently. Such framework typically employs the Model Average approach, denoted as MA-DNN, in which parallel workers conduct respective training based on their own local data while the parameters of local models are periodically communicated and averaged to obtain a global model which serves as the new start of local models. However, since DNN is a highly non-convex model, averaging parameters cannot ensure that such global model can perform better than those local models. To tackle this problem, we introduce a new parallel training framework called Ensemble-Compression, denoted as EC-DNN. In this framework, we propose to aggregate the local models by ensemble, i.e., averaging the outputs of local models instead of the parameters. As most of prevalent loss functions are convex to the output of DNN, the performance of ensemble-based global model is guaranteed to be at least as good as the average performance of local models. However, a big challenge lies in the explosion of model size since each round of ensemble can give rise to multiple times size increment. Thus, we carry out model compression after each ensemble, specialized by a distillation based method in this paper, to reduce the size of the global model to be the same as the local ones. Our experimental results demonstrate the prominent advantage of EC-DNN over MA-DNN in terms of both accuracy and speedup.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Besides handling very large networks, distributed or parallelized approaches offer other advantages, such as improved ensembling [400] or accelerated hyperparameter optimization [401,402].”
Model Aggregation via Good-Enough Model Spaces (2018, background): “Averaging can also perform arbitrarily poorly in non-convex settings, particularly when the local models converge to differing local optima [18, 27].”