Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning
This work addresses efficient network compression for edge devices like smartphones, offering an incremental improvement over existing pruning methods.
The paper tackles the NP-hard problem of optimal network pruning by proposing a two-stage pruning approach guided by Fourier analysis, which outperforms traditional magnitude-based pruning algorithms on CIFAR-10 and CIFAR-100 datasets.
With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge devices, such as smartphones or tablets. However, optimal network pruning is a non-trivial task which mathematically is an NP-hard problem. Previous researchers explain training a pruned network as buying a lottery ticket. In this paper, we investigate the Magnitude-Based Pruning (MBP) scheme and analyze it from a novel perspective through Fourier analysis on the deep learning model to guide model designation. Besides explaining the generalization ability of MBP using Fourier transform, we also propose a novel two-stage pruning approach, where one stage is to obtain the topological structure of the pruned network and the other stage is to retrain the pruned network to recover the capacity using knowledge distillation from lower to higher on the frequency domain. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate the superiority of our novel Fourier analysis based MBP compared to other traditional MBP algorithms.