Fairway：一种构建公平ML软件的方法
Fairway: A Way to Build Fair ML Software
摘要：
机器学习软件正越来越多地用于做出影响人们生活的决策。但有时候，这个软件的核心部分（学习模型）会以一种有偏见的方式表现出来，给特定群体带来不必要的优势（这些群体是由性别、种族等决定的）。人工智能软件系统中的这种“算法歧视”已经成为机器学习和软件工程社区严重关注的问题。在软件系统中，已经有一些工作是为了发现“算法偏见“或“伦理偏差”。一旦在人工智能软件系统中检测到偏差，减轻偏差就非常重要。在这项工作中，我们a）解释训练数据中的地面真实偏差如何影响机器学习模型的公平性以及如何在AI软件中发现这种偏差，b）提出一种结合预处理和处理方法的方法Fairway，以消除训练数据和训练模型中的道德偏见。我们的研究结果表明，我们可以在学习模型中发现偏差并减轻偏差，而不会对该模型的预测性能造成太大损害。我们建议（1）测试偏差和（2）偏差缓解应该是机器学习软件开发生存周期的常规部分。Fairway为这两个目的提供了很多支持。
英文摘要：
Machine learning software is increasingly being used to make decisions that affect people's lives. But sometimes, the core part of this software (the learned model), behaves in a biased manner that gives undue advantages to a specific group of people (where those groups are determined by sex, race, etc.). This "algorithmic discrimination" in the AI software systems has become a matter of serious concern in the machine learning and software engineering community. There have been works done to find "algorithmic bias" or "ethical bias" in the software system. Once the bias is detected in the AI software system, the mitigation of bias is extremely important. In this work, we a)explain how ground-truth bias in training data affects machine learning model fairness and how to find that bias in AI software,b)propose a methodFairwaywhich combines pre-processing and in-processing approach to remove ethical bias from training data and trained model. Our results show that we can find bias and mitigate bias in a learned model, without much damaging the predictive performance of that model. We propose that (1) test-ing for bias and (2) bias mitigation should be a routine part of the machine learning software development life cycle. Fairway offers much support for these two purposes.
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。
