How to ensure fairness in algorithmic decision making models is an important task in machine learning [12,15]. Over the past years, many researchers have been devoted to the design of fair classification algorithms withrespecttoapre-defined protected attribute,suchasraceorsex,anda decision task/model, such as hiring [1,11,24]. In particular,one line of the work istoincorporate fairness constraints into classic learning algorithms tobuild fair classifiers from potentially biased data [4,13,29,31-33]. Most of previous research generally focuses on a single decision model.

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently.

One ofthe most important tasks invideo understanding istounderstand human actions, which is one of the representativetasks for video understanding [54].

Stein discrepancies (SDs) monitor convergence andnon-convergence inapprox-imate inference when exact integration and sampling are intractable. However,the computation of a Stein discrepancy can be prohibitive if the Stein operator - often a sum over likelihood terms or potentials - is expensive to evaluate.