Algorithm Bias Detection and Mitigation in Lenovo Face Recognition Engine
With the advancement of Artificial Intelligence(AI),algo-rithms brings more fairness challenges in ethical,legal,psychological and social levels.People should start to face these challenges seriously in dealing with AI products and AI solutions.More and more companies start to recognize the importance of Diversity and Inclusion(D&I)due to AI algorithms and take corresponding actions.This paper introduces Lenovo AI's Vision on D&I,specially,the efforts of mitigating algorithm bias in human face processing technology.Latest evaluation shows that Lenovo face recognition engine achieves better performance of racial fair-ness over competitors in terms of multiple metrics.In addition,it also presents post-processing strategy of improving fairness according to dif-ferent considerations and criteria.
Explainable Artificial Intelligence Diversity and inclusion Algorithm fairness Bias detection and mitigation
Sheng Shi Shanshan Wei Zhongchao Shi Yangzhou Dui Wei Fan Jianping Fan Yolanda Conyers Feiyu Xu
AI Lab,Lenovo Research,Beijing,China Lenovo Group,Morrisville,USA SAP Cloud,Walldorf,Germany
国际会议
9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)
郑州
英文
1293-1304
2020-10-14（万方平台首次上网日期，不代表论文的发表时间）