Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
复制标题
DOI：
10.1145/3534678.3539420
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Chenxu Zhao;Feng Mi;Xintao Wu;Kai Jiang;L. Khan;Feng Chen
中科院分区：
文献类型：
--
作者：
Chenxu Zhao;Feng Mi;Xintao Wu;Kai Jiang;L. Khan;Feng Chen
公平意识的在线学习框架已经成为持续终身学习环境的一个强大工具。学习器的目标是顺序地学习新任务，其中新任务随着时间的推移一个接一个地出现，并且学习器确保新任务在不同的受保护子群体（例如种族和性别）中的统计平等。现有方法的一个主要缺点是，他们大量使用的独立同分布假设的数据，因此提供静态后悔分析的框架。然而，低静态遗憾并不意味着在不断变化的环境中，任务是从异构分布采样的良好性能。为了解决在不断变化的环境中的公平意识的在线学习问题，在本文中，我们首先构建了一个新的遗憾度量FairSAR通过添加长期的公平性约束到一个强适应的损失遗憾。此外，为了在每一轮确定一个好的模型参数，我们提出了一种新的自适应公平意识在线元学习算法，即FairSAOML，它能够适应不断变化的环境中的偏差控制和模型精度。该问题的形式制定了一个双层凸-凹优化模型的原始和对偶参数，分别与模型的准确性和公平性。理论分析提供了损失后悔和违反累积公平约束的次线性上界。我们对不同的真实世界的数据集与不断变化的环境设置的实验评估表明，所提出的FairSAOML显着优于基于最佳的先验在线学习方法的替代品。
The fairness-aware online learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for the learner is to sequentially learn new tasks where they come one after another over time and the learner ensures the statistic parity of the new coming task across different protected sub-populations (e.g. race and gender). A major drawback of existing methods is that they make heavy use of the i.i.d assumption for data and hence provide static regret analysis for the framework. However, low static regret cannot imply a good performance in changing environments where tasks are sampled from heterogeneous distributions. To address the fairness-aware online learning problem in changing environments, in this paper, we first construct a novel regret metric FairSAR by adding long-term fairness constraints onto a strongly adapted loss regret. Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision. The problem is formulated in the form of a bi-level convex-concave optimization with respect to the model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The theoretic analysis provides sub-linear upper bounds for both loss regret and violation of cumulative fairness constraints. Our experimental evaluation on different real-world datasets with settings of changing environments suggests that the proposed FairSAOML significantly outperforms alternatives based on the best prior online learning approaches.