arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.19318cs.AIcs.GT
收藏

基于Shapley-Owen效应的公平性分析

Fairness Analysis with Shapley-Owen Effects

Chalmers University of Technology(查尔姆斯理工大学);Entalus(恩塔勒斯公司)

Harald Ruess

AI总结:

本文提出通过Shapley-Owen效应的谱分解将公平性归因计算拆分为模型无关与模型特定部分,并利用多项式混沌展开系数解析计算,同时给出稀疏截断算法和误差上界。

摘要:

我们认为,相对重要性及其在Shapley-Owen效应意义上的公平归因是一种恰当的衡量方式,并且,如果我们接受少数合理的公平归因要求,那么这是衡量公平性的唯一途径。另一方面,Shapley-Owen效应的计算可能非常耗费资源。我们的主要技术结果是对Shapley-Owen效应进行谱分解,从而将这些指标的计算分解为模型特定部分和模型无关部分。模型无关部分只需预先计算一次,而Shapley-Owen效应的模型特定计算则通过模型的多项式混沌展开(PCE)系数解析地表示,这些系数现在可以被复用来计算不同的Shapley-Owen效应。我们还提出了一种算法,用于计算模型PCE的精确且稀疏的截断以及Shapley-Owen效应的谱分解,同时给出累积近似误差的上界。PCE和Shapley-Owen效应的近似都会收敛到其真实值。

英文摘要:

We argue that relative importance and its equitable attribution in terms of Shapley-Owen effects is an appropriate one, and, if we accept a small number of reasonable imperatives for equitable attribution, the only way to measure fairness. On the other hand, the computation of Shapley-Owen effects can be very demanding. Our main technical result is a spectral decomposition of the Shapley-Owen effects, which decomposes the computation of these indices into a model-specific and a model-independent part. The model-independent part is precomputed once and for all, and the model-specific computation of Shapley-Owen effects is expressed analytically in terms of the coefficients of the model's \emph{polynomial chaos expansion} (PCE), which can now be reused to compute different Shapley-Owen effects. We also propose an algorithm for computing precise and sparse truncations of the PCE of the model and the spectral decomposition of the Shapley-Owen effects, together with upper bounds on the accumulated approximation errors. The approximations of both the PCE and the Shapley-Owen effects converge to their true values.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑