Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsically embedded into the models due to the discrimination in the training data. As a countermeasure, fairness testing systemically identifies discriminatory samples, which can be used to retrain the model and improve the model's fairness. Existing fairness testing approaches however have two major limitations. Firstly, they only work well on traditional machine learning models and have poor performance (e.g., effectiveness and efficiency) on deep learning models. Secondly, they only work on simple structured (e.g., tabular) data and are not applicable for domains such as text. In this work, we bridge the gap by proposing a scalable and effective approach for systematically searching for discriminatory samples while extending existing fairness testing approaches to address a more challenging domain, i.e., text classification. Compared with state-of-the-art methods, our approach only employs lightweight procedures like gradient computation and clustering, which is significantly more scalable and effective. Experimental results show that on average, our approach explores the search space much more effectively (9.62 and 2.38 times more than the state-of-the-art methods respectively on tabular and text datasets) and generates much more discriminatory samples (24.95 and 2.68 times) within a same reasonable time. Moreover, the retrained models reduce discrimination by 57.2% and 60.2% respectively on average.
翻译:虽然深层次的学习在许多应用中表现出惊人的成绩,但人们仍然对它是否可靠感到关切; 深层次的学习应用对社会有影响的可取属性之一是公平(即不歧视); 不幸的是,由于培训数据中的歧视,歧视可能内在地嵌入模型中。 作为一种反措施,公平测试系统化地查明歧视性样本,可以用来重新培训模型,改进模型的公正性。 现有的公平测试方法有两大局限性。 首先,它们仅仅在传统机器学习模式上运作良好,在深层次学习模式上业绩不佳(例如,效能和效率)。 其次,它们只处理结构简单(例如,表格)的数据,而不适用于文本等领域。 在这项工作中,我们提出一个可扩展现有公平测试方法以解决更具挑战性的领域,即文本分类。 首先,它们只对传统机器学习模式运作良好,在深度计算和组合方面业绩差(例如,效能和效益)。 其次,实验结果显示,系统搜索歧视性的样本分别比平均时间(9.95)要多得多。 在平均时间里,对平均的样本进行更精确地分析。 (9.95) 和表格中,对平均时间方法进行了更多的再分析。 。