%0 Conference Proceedings
%T Data Fine-Pruning: A Simple Way to Accelerate Neural Network Training
%+ University of Warwick [Coventry]
%+ Shenzhen University
%A Li, Junyu
%A He, Ligang
%A Ren, Shenyuan
%A Mao, Rui
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 15th IFIP International Conference on Network and Parallel Computing (NPC)
%C Muroran, Japan
%Y Feng Zhang
%Y Jidong Zhai
%Y Marc Snir
%Y Hai Jin
%Y Hironori Kasahara
%Y Mateo Valero
%I Springer International Publishing
%3 Network and Parallel Computing
%V LNCS-11276
%P 114-125
%8 2018-11-29
%D 2018
%R 10.1007/978-3-030-05677-3_10
%K Deep Neural Network
%K Data pruning
%K SGD
%K Acceleration
%Z Computer Science [cs]Conference papers
%X The training process of a neural network is the most time-consuming procedure before being deployed to applications. In this paper, we investigate the loss trend of the training data during the training process. We find that given a fixed set of hyper-parameters, pruning specific types of training data can reduce the time consumption of the training process while maintaining the accuracy of the neural network. We developed a data fine-pruning approach, which can monitor and analyse the loss trend of training instances at real-time, and based on the analysis results, temporarily pruned specific instances during the training process basing on the analysis. Furthermore, we formulate the time consumption reduced by applying our data fine-pruning approach. Extensive experiments with different neural networks are conducted to verify the effectiveness of our method. The experimental results show that applying the data fine-pruning approach can reduce the training time by around 14.29% while maintaining the accuracy of the neural network.
%G English
%Z TC 10
%Z WG 10.3
%2 https://inria.hal.science/hal-02279554/document
%2 https://inria.hal.science/hal-02279554/file/477597_1_En_10_Chapter.pdf
%L hal-02279554
%U https://inria.hal.science/hal-02279554
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC10
%~ IFIP-NPC
%~ IFIP-WG10-3
%~ IFIP-LNCS-11276