Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamics
Donald Martin, Jr. Google、Vinodkumar Prabhakaran Google、Jill Kuhlberg System Stars、Andrew Smart Google、William S. Isaac DeepMind
Abstract
Recent research on algorithmic fairness has highlighted that the problem formulation phase of ML system development can be a key source of bias that has significant downstream impacts on ML system fairness outcomes. However, very little attention has been paid to methods for improving the fairness efficacy of this critical phase of ML system development. Current practice neither accounts for the dynamic complexity of high-stakes domains nor incorporates the perspectives of vulnerable stakeholders. In this paper we introduce community based system dynamics (CBSD) as an approach to enable the participation of typically excluded stakeholders in the problem formulation phase of the ML system development process and facilitate the deep problem understanding required to mitigate bias during this crucial stage.
中文速览
机器学习系统在医疗、司法等高风险领域造成的歧视性后果，很大程度上根源于开发最初的"问题定义"阶段——开发者用不恰当的代理变量简化问题、忽略社会系统的动态反馈，同时又把受影响最深的边缘群体排除在决策之外。本文提出将"基于社区的系统动力学"（Community Based System Dynamics, CBSD）引入这一阶段：通过因果回路图和存量流量图等可视化工具，将各方因果假设显式呈现，再借助计算机仿真验证动态假设，并以参与式建模的方式让边缘社区成员真正参与共建因果模型，而非仅充当信息提供者。以信用评分贷款系统和医疗风险评估算法为例，作者展示了CBSD如何捕捉时间延迟与反馈回路、暴露代理变量的偏差，以及如何把受影响群体的生活经验转化为建模数据。这一方法的重要性在于，它为目前仍依赖少数决策者直觉的问题定义阶段提供了一套结构化、透明且具有包容性的框架，有望从源头减少算法歧视，而非在模型训练完成后再做事后补救。
原文 arXiv:2005.07572;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2005.07572v3