Making Fair ML Software using Trustworthy Explanation
Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having a huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some sensitive attributes such as sex, race etc. Prior works concentrated on finding and mitigating bias in ML models. A recent trend is using instance-based model agnostic explanation methods such as LIME[1] to find out bias in the model prediction. Our work concentrates on finding shortcomings of current bias measures and explanation methods. We show how our proposed method based on K nearest neighbors can overcome those shortcomings and find the underlying bias of black-box models. Our results are more trustworthy and helpful for the practitioners. Finally, We describe our future framework combining explanation and planning to build fair software
Wed 23 Sep Times are displayed in time zone: (UTC) Coordinated Universal Time
00:00 - 01:00: Software Engineering for AI (1)Research Papers / NIER track at Kangaroo Chair(s): Song WangYork University, Canada | |||
00:00 - 00:20 Talk | Multiple-Boundary Clustering and Prioritization to Promote Neural Network Retraining Research Papers Weijun ShenNanjing University, Yanhui LiDepartment of Computer Science and Technology, Nanjing University, Lin ChenNanjing University, YuanLei HanNanjing University, Yuming ZhouNanjing University, Baowen XuState Key Laboratory for Novel Software Technology, Nanjing University | ||
00:20 - 00:40 Talk | MARBLE: Model-Based Robustness Analysis of Stateful Deep Learning Systems Research Papers Xiaoning DuNanyang Technological University, Yi LiNanyang Technological University, Singapore, Xiaofei XieNanyang Technological University, Lei MaKyushu University, Yang LiuNanyang Technological University, Singapore, Jianjun ZhaoKyushu University | ||
00:40 - 00:50 Talk | Making Fair ML Software using Trustworthy Explanation NIER track Joymallya ChakrabortyNorth Carolina State University, USA, Kewen PengNorth Carolina State University, Tim MenziesNorth Carolina State University, USA Link to publication DOI Pre-print Media Attached |