In the context of online privacy, many methods propose complex privacy and security preserving measures to protect sensitive data. In this paper, we argue that: not storing any sensitive data is the best form of security. Thus we propose an online framework that "burns after reading", i.e. each online sample is immediately deleted after it is processed. Meanwhile, we tackle the inevitable distribution shift between the labeled public data and unlabeled private data as a problem of unsupervised domain adaptation. Specifically, we propose a novel algorithm that aims at the most fundamental challenge of the online adaptation setting--the lack of diverse source-target data pairs. Therefore, we design a Cross-Domain Bootstrapping approach, called CroDoBo, to increase the combined diversity across domains. Further, to fully exploit the valuable discrepancies among the diverse combinations, we employ the training strategy of multiple learners with co-supervision. CroDoBo achieves state-of-the-art online performance on four domain adaptation benchmarks.
翻译:在网上隐私方面,许多方法都提出了保护敏感数据的复杂的隐私和安全保护措施。在本文中,我们争论道:不存储任何敏感数据是最佳的安全形式。因此,我们提议了一个“阅读后烧伤”的在线框架,即每个在线样本在处理后立即删除。与此同时,我们处理标签公共数据和未贴标签的私人数据之间不可避免的分配变化,认为这是一个不受监督的域适应问题。具体地说,我们提议了一个新的算法,目的是应对网上适应设置的最根本挑战,即缺乏不同的源目标数据对口。因此,我们设计了一个跨域博茨特拉普方法,称为克罗多博,以增加跨域的综合多样性。此外,为了充分利用不同组合之间的宝贵差异,我们采用了与共同监督的多位学习者的培训战略。CroDobo在四个域适应基准上实现了最先进的在线业绩。