Robust Unsupervised Domain Adaptation from A Corrupted Source
Robust Unsupervised Domain Adaptation from A Corrupted Source
复制标题
DOI：
10.1109/icdm54844.2022.00171
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Shuyang Yu;Zhuangdi Zhu;Boyang Liu;Anil K. Jain;Jiayu Zhou
中科院分区：
文献类型：
--
作者：
Shuyang Yu;Zhuangdi Zhu;Boyang Liu;Anil K. Jain;Jiayu Zhou
无监督领域自适应(UDA)为无监督学习提供了一种很有前途的解决方案，它通过可访问的标记训练数据来传输来自相关源域的知识。现有的UDA解决方案依赖于来自源域的具有短尾分布的干净训练数据，当源域数据被内在地或通过敌意攻击破坏时，该数据可能是脆弱的。在这项工作中，我们提出了一个有效的框架，以原则性的方式应对来自受破坏源域的UDA挑战。具体地说，我们从多个领域不变模型中进行知识集成，这些模型是在训练数据的随机分区上学习的。为了进一步解决从源域到目标域的分布转移，我们通过互信息最大化对每个学习模型进行精化，以高置信度自适应地获得目标域的预测信息。大量的实验研究表明，该方法对各种类型的有毒数据攻击具有较强的鲁棒性，同时在目标域上取得了较高的渐近性能。
Unsupervised Domain Adaptation (UDA) provides a promising solution for learning without supervision, which transfers knowledge from relevant source domains with accessible labeled training data. Existing UDA solutions hinge on clean training data with a short-tail distribution from the source domain, which can be fragile when the source domain data is corrupted either inherently or via adversarial attacks. In this work, we propose an effective framework to address the challenges of UDA from corrupted source domains in a principled manner. Specifically, we perform knowledge ensemble from multiple domain-invariant models that are learned on random partitions of training data. To further address the distribution shift from the source to the target domain, we refine each of the learned models via mutual information maximization, which adaptively obtains the predictive information of the target domain with high confidence. Extensive empirical studies demonstrate that the proposed approach is robust against various types of poisoned data attacks while achieving high asymptotic performance on the target domain.