arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.08700cs.CV
收藏

预训练模型中的彩票大奖

Lottery Jackpots Exist in Pre-trained Models

Xiamen University(厦门大学);Tencent(腾讯)

Yuxin Zhang, Mingbao Lin, Yunshan Zhong, Fei Chao, Rongrong Ji

AI总结:

本文发现预训练模型中存在无需权重训练的高性能稀疏子网络“彩票大奖”,并提出基于幅度剪枝初始化和短限制方法,实现高效搜索,在ResNet-50上移除90%权重且保持高精度。

摘要:

网络剪枝是一种有效的降低网络复杂度且性能损失可接受的方法。现有研究通过耗时的权重训练或对扩展宽度的网络进行复杂搜索来实现神经网络的稀疏性,这极大地限制了网络剪枝的应用。本文表明,在不涉及权重训练且宽度未扩展的预训练模型中,存在高性能且稀疏的子网络,称为“彩票大奖”。此外,我们从两个角度提高了搜索彩票大奖的效率。首先,我们观察到许多现有剪枝准则导出的稀疏掩码与我们的彩票大奖搜索掩码有高度重叠,其中基于幅度的剪枝产生的掩码与我们的最相似。因此,我们搜索到的彩票大奖在ResNet-50上移除了90%的权重,而在ImageNet上仅用5个搜索周期就轻松获得超过70%的top-1准确率。基于这一发现,我们使用基于幅度的剪枝初始化稀疏掩码,使得彩票大奖搜索成本至少降低3倍,同时达到相当甚至更好的性能。其次,我们对彩票大奖的搜索过程进行了深入分析。我们的理论结果表明,权重搜索过程中训练损失的下降可能受到现代网络中权重之间依赖性的干扰。为了缓解这一问题,我们提出了一种新颖的短限制方法,以限制可能对训练损失产生潜在负面影响的掩码变化。我们的代码可在https://github.com/zyxxmu/lottery-jackpots获取。

英文摘要:

Network pruning is an effective approach to reduce network complexity with acceptable performance compromise. Existing studies achieve the sparsity of neural networks via time-consuming weight training or complex searching on networks with expanded width, which greatly limits the applications of network pruning. In this paper, we show that high-performing and sparse sub-networks without the involvement of weight training, termed "lottery jackpots", exist in pre-trained models with unexpanded width. Furthermore, we improve the efficiency for searching lottery jackpots from two perspectives. Firstly, we observe that the sparse masks derived from many existing pruning criteria have a high overlap with the searched mask of our lottery jackpot, among which, the magnitude-based pruning results in the most similar mask with ours. Consequently, our searched lottery jackpot removes 90% weights in ResNet-50, while it easily obtains more than 70% top-1 accuracy using only 5 searching epochs on ImageNet. In compliance with this insight, we initialize our sparse mask using the magnitude-based pruning, resulting in at least 3x cost reduction on the lottery jackpot searching while achieving comparable or even better performance. Secondly, we conduct an in-depth analysis of the searching process for lottery jackpots. Our theoretical result suggests that the decrease in training loss during weight searching can be disturbed by the dependency between weights in modern networks. To mitigate this, we propose a novel short restriction method to restrict change of masks that may have potential negative impacts on the training loss. Our code is available at https://github.com/zyxxmu/lottery-jackpots.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑