论文标题
FR-TRAIN：一种基于信息的公平和强大培训的方法
FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
论文作者
论文摘要
值得信赖的AI是机器学习的关键问题，除了训练准确的模型外，还必须考虑在存在数据偏见和中毒的情况下公平和强大的培训。但是，现有的模型公平技术错误地将中毒的数据视为要固定的额外偏见，从而导致严重的性能下降。为了解决这个问题，我们提出了FR-TRAIN，从而整体上执行了公平而健壮的模型培训。我们提供基于信息的基于信息的仅基于对抗性培训的公平方法的相互解释，并将此想法应用于建筑师的其他歧视者，该歧视者可以使用干净的验证集识别有毒数据并降低其影响力。在我们的实验中，通过减轻偏见和防御中毒的防御，FR-Train在存在数据中毒的情况下几乎没有降低公平和准确性。我们还演示了如何使用众包构建清洁验证集并发布新的基准数据集。
Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, resulting in severe performance degradation. To address this problem, we propose FR-Train, which holistically performs fair and robust model training. We provide a mutual information-based interpretation of an existing adversarial training-based fairness-only method, and apply this idea to architect an additional discriminator that can identify poisoned data using a clean validation set and reduce its influence. In our experiments, FR-Train shows almost no decrease in fairness and accuracy in the presence of data poisoning by both mitigating the bias and defending against poisoning. We also demonstrate how to construct clean validation sets using crowdsourcing, and release new benchmark datasets.
