151 citations · 424 across the 27 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Defense Against Explanation Manipulation
Ruixiang Tang, Ninghao Liu, Fan Yang +2
Explainable machine learning attracts increasing attention as it improves transparency of models, which is helpful for machine learning to be trusted in real applications. However,…
cs.LG2021★ 28 cited
Fairness via Representation Neutralization
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang +3
Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attri…