arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.06359cs.LGcs.AI
收藏

Federated Pruning:利用联邦学习提高神经网络效率

Federated Pruning: Improving Neural Network Efficiency with Federated Learning

Emory University(埃默里大学);Google LLC(谷歌有限责任公司)

Rongmei Lin, Yonghui Xiao, Tien-Ju Yang, Ding Zhao, Li Xiong, Giovanni Motta, Françoise Beaufays

摘要:

自动语音识别模型需要大量的语音数据进行训练,而这些数据的收集往往会导致隐私问题。联邦学习已经被广泛使用,并且被认为是一种有效的分散技术,通过协作学习共享的预测模型,同时将数据保持在不同客户端设备上的本地。然而,客户端设备上有限的计算和通信资源为大型模型带来了实际困难。为了克服这些挑战,我们提出了联邦修剪训练联邦设置下的简化模型,同时保持类似的性能相比,完整的模型。此外,与集中式训练相比,还可以利用大量的客户端数据来改善修剪结果。我们探索不同的修剪方案,并提供我们的方法的有效性的经验证据。

英文摘要:

Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective decentralized technique by collaboratively learning a shared prediction model while keeping the data local on different clients devices. However, the limited computation and communication resources on clients devices present practical difficulties for large models. To overcome such challenges, we propose Federated Pruning to train a reduced model under the federated setting, while maintaining similar performance compared to the full model. Moreover, the vast amount of clients data can also be leveraged to improve the pruning results compared to centralized training. We explore different pruning schemes and provide empirical evidence of the effectiveness of our methods.

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。

↑