实时监控算法公平性，防止决策系统对特定群体产生偏见。
Stream-Based Monitoring of Algorithmic Fairness
- 用时序逻辑语言RTLola定义公平性规范，实现运行时动态监控。
- 在真实数据集COMPAS上验证，有效检测出系统对不同群体的偏差。
- 适合关注算法伦理、需实时保障公平性的产品团队或监管机构。
自动化决策与预测系统广泛应用于贷款信用评估、被告再犯风险预测等关乎民生的重要场景，这类系统必须避免对社会群体产生偏见。然而，由于系统常包含复杂的机器学习组件且输入空间庞大，静态验证公平性往往不可行。为此，本文提出基于数据流的运行时监控方法，通过时序逻辑语言RTLola形式化定义算法公平性规范，并在多个基准测试中验证其有效性。除了展示在大规模数据流上的高效性外，还在真实世界数据集COMPAS上进行了评估，结果表明该方法能有效识别系统中的群体偏差。
原文摘要 · Abstract (English)
Automatic decision and prediction systems are increasingly deployed in applications where they significantly impact the livelihood of people, such as for predicting the creditworthiness of loan applicants or the recidivism risk of defendants. These applications have given rise to a new class of algorithmic-fairness specifications that require the systems to decide and predict without bias against social groups. Verifying these specifications statically is often out of reach for realistic systems, since the systems may, e.g., employ complex learning components, and reason over a large input space. In this paper, we therefore propose stream-based monitoring as a solution for verifying the algorithmic fairness of decision and prediction systems at runtime. Concretely, we present a principled way to formalize algorithmic fairness over temporal data streams in the specification language RTLola and demonstrate the efficacy of this approach on a number of benchmarks. Besides synthetic scenarios that particularly highlight its efficiency on streams with a scaling amount of data, we notably evaluate the monitor on real-world data from the recidivism prediction tool COMPAS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。