Zhang, J; Harman, M; (2021) "Ignorance and Prejudice" in Software Fairness. In: (Proceedings) 43th International Conference on Software Engineering. IEEE: Virtual conference. (In press).

Preview

Text ICSE2021__Ignorance_Prejudice (5).pdf - Published Version Download (1MB) | Preview

Abstract

Abstract—Machine learning software can be unfair when making human-related decisions, having prejudices over cer- tain groups of people. Existing work primarily focuses on proposing fairness metrics and presenting fairness improvement approaches. It remains unclear how key aspect of any machine learning system, such as feature set and training data, affect fairness. This paper presents results from a comprehensive study that addresses this problem. We find that enlarging the feature set plays a significant role in fairness (with an average effect rate of 38%). Importantly, and contrary to widely-held beliefs that greater fairness often corresponds to lower accuracy, our findings reveal that an enlarged feature set has both higher accuracy and fairness. Perhaps also surprisingly, we find that a larger training data does not help to improve fairness. Our results suggest a larger training data set has more unfairness than a smaller one when feature sets are insufficient; an important cautionary finding for practising software engineers.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item