arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.11997cs.SDcs.LGeess.AS
收藏

基于联邦自监督学习的声事件分类

Federated Self-Supervised Learning for Acoustic Event Classification

Massachusetts Institute of Technology(麻省理工学院);Amazon.com Inc(亚马逊公司)

Meng Feng, Chieh-Chi Kao, Qingming Tang, Ming Sun, Viktor Rozgic, Spyros Matsoukas, Chao Wang

摘要:

标准声学事件分类(AEC)解决方案需要从客户端设备大规模收集数据以进行模型优化。联邦学习(FL)是一个引人注目的框架,它将数据汇集和模型训练结合起来,以增强客户隐私。在这项工作中,我们调查的可行性,应用FL,以提高AEC性能,而没有客户数据可以直接上传到服务器。我们假设没有伪标签可以从设备上的用户输入中推断出来,与AEC的典型用例保持一致。我们将自监督学习适应于FL框架,用于表示的设备上持续学习,并且在没有标记/伪标记数据的情况下,它可以提高下游AEC分类器的性能。与基线w/o FL相比,该方法在保持召回率的同时,相对提高了准确率高达20.3%。我们的工作与FL之前的工作不同,因为我们的方法不需要用户生成的学习目标,我们使用的数据是从我们的Beta程序中收集的,并且是去识别的,以最大限度地模拟生产环境。

英文摘要:

Standard acoustic event classification (AEC) solutions require large-scale collection of data from client devices for model optimization. Federated learning (FL) is a compelling framework that decouples data collection and model training to enhance customer privacy. In this work, we investigate the feasibility of applying FL to improve AEC performance while no customer data can be directly uploaded to the server. We assume no pseudo labels can be inferred from on-device user inputs, aligning with the typical use cases of AEC. We adapt self-supervised learning to the FL framework for on-device continual learning of representations, and it results in improved performance of the downstream AEC classifiers without labeled/pseudo-labeled data available. Compared to the baseline w/o FL, the proposed method improves precision up to 20.3\% relatively while maintaining the recall. Our work differs from prior work in FL in that our approach does not require user-generated learning targets, and the data we use is collected from our Beta program and is de-identified, to maximally simulate the production settings.

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。

↑