{"id":613,"date":"2020-02-25T21:24:40","date_gmt":"2020-02-25T21:24:40","guid":{"rendered":"http:\/\/wordpress.cs.vt.edu\/cs6724s20\/?p=613"},"modified":"2020-02-25T21:24:40","modified_gmt":"2020-02-25T21:24:40","slug":"02-26-20-fanglan-chen-explaining-models-an-empirical-study-of-how-explanations-impact-fairness-judgment","status":"publish","type":"post","link":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/2020\/02\/25\/02-26-20-fanglan-chen-explaining-models-an-empirical-study-of-how-explanations-impact-fairness-judgment\/","title":{"rendered":"02\/26\/20 \u2013 Fanglan Chen \u2013 Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment"},"content":{"rendered":"\n

Summary<\/strong><\/p>\n\n\n\n

Dodge et al.\u2019s paper \u201cExplaining Models: An Empirical Study of How Explanations Impact Fairness Judgment\u201d presents an empirical study on how people make fairness judgments of machine learning systems and how different styles of explanation impact their judgments. Fairness issues of ML systems attract research interests during recent years. Mitigating the unfairness in ML systems is challenging, which requires the good cooperation of  developers, users, and the general public. The researchers state that how explanations are constructed have an impact on users\u2019 confidence in the systems. To further examine the potential impacts on people\u2019s fairness judgments of ML systems, they conduct empirical experiments involving crowdsourcing workers on four types of programmatically generated explanations (influence, demographic-based, sensitivity, and case-based). Their key findings include: 1) some explanations are considered more fair, while others have negative impact on users\u2019 trust of the algorithm in regards of fairness; 2) varied fairness issues (model-wide fairness and case-specific fairness) can be detected more effectively through an examination of different explanation styles; 3) individual differences (prior positions and judgment criteria of algorithmic fairness) lead to how users react to different styles of explanation. 
<\/p>\n\n\n\n

Reflection<\/strong><\/p>\n\n\n\n

This paper shines light on a very important fact that bias in ML systems can be detected and mitigated. There is a growing attention to the fairness issues in AI-powered technologies in the machine learning research community. Since ML algorithms are widely used to speed up the decision making process in a variety of domains, beyond achieving good performance, they are expected to produce neutral results. There is no denying the fact that algorithms rely on data, \u201cgarbage in, garbage out.\u201d Hence, it is incumbent to feed the unbiased data to these systems upon developers in the first place. In many real-world cases, race is actually not used as an input, however, it correlates to other factors that make predictions biased. That case is not as easy as the cases presented in the paper to detect but still requires effort to be corrected. A question here would be in order to counteract this implicit bias, should race be considered and used to calibrate the relative importance of other factors? 
<\/p>\n\n\n\n

Besides the bias introduced by data input, there are other factors that need to be taken into consideration to deal with the fairness issues in ML systems. Firstly, machine bias can never be neglected. The term bias in the context of the high-stakes tasks (e.g. future criminal prediction) is very important because a false positive decision could have a destructive impact on a person’s life. This is why when an AI system deals with the human subject (in this case human life), the system must be highly precise and accurate and ideally provide reasonable explanation. Making a person’s life harder to live in a society or impacting badly a person’s life due to a flawed computer model is never acceptable. Secondly, the proprietary model is another concern. One thing should be kept in mind that many high-stacks tasks such as future criminal prediction is a matter of public matter and should be transparent and fair. That does not mean that the ML systems used for those tasks need to be completely public and open. However, I believe there should be a regulatory board of experts who can verify and validate the ML systems. More specifically, the experts can verify and validate the risk factors used in a system so that the factors could be widely accepted. They can also verify and validate the algorithmic techniques used in a system so that the system incorporates less bias. 
<\/p>\n\n\n\n

Discussion<\/strong><\/p>\n\n\n\n

I think the following questions are worthy of further discussion.<\/p>\n\n\n\n