用综合数据生成器调查偏差:经验证据和哲学解释
Investigating Bias with a Synthetic Data Generator: Empirical Evidence and Philosophical Interpretation
摘要:
机器学习应用在我们的社会中变得越来越普遍。由于这些决策系统依赖于数据驱动的学习,风险在于它们将系统地传播数据中嵌入的偏见。在本文中,我们建议通过引入一个框架来分析偏差,该框架用于生成具有特定类型偏差及其组合的合成数据。我们深入研究这些偏见的性质,讨论它们与道德和正义框架的关系。最后,我们利用我们提出的合成数据生成器在不同的情况下进行实验,各种偏见的组合。因此,我们分析了偏见对非缓解和缓解机器学习模型中的性能和公平性指标的影响。
英文摘要:
Machine learning applications are becoming increasingly pervasive in our society. Since these decision-making systems rely on data-driven learning, risk is that they will systematically spread the bias embedded in data. In this paper, we propose to analyze biases by introducing a framework for generating synthetic data with specific types of bias and their combinations. We delve into the nature of these biases discussing their relationship to moral and justice frameworks. Finally, we exploit our proposed synthetic data generator to perform experiments on different scenarios, with various bias combinations. We thus analyze the impact of biases on performance and fairness metrics both in non-mitigated and mitigated machine learning models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。