Human-Compatible Artificial Intelligence with Guarantees (AutoFair)

在本提案中，我们使用受控制理论启发的方法来解决人工智能的透明度和可解释性问题。值得注意的是，我们考虑对人工智能管道、某些闭环和更复杂的互连进行全面而灵活的特性认证。在一个极端情况下，人们可以考虑通过对训练过程中某些偏差度量的硬约束来规避风险的先验保证。在另一个极端，人们可以考虑对人工智能管道选择所涉及的确切权衡进行细致入微的沟通，以及它们对工业和偏见结果的影响。这两种极端在优化管道方面几乎没有提供任何帮助，并且在解释管道的公平性相关质量方面缺乏灵活性。为了寻求中间立场，我们建议通过预处理、训练、推理和具有某些属性的后处理步骤的模块化组合，对人工智能管道中与公平性相关的质量进行先验认证。此外，我们提出了一个广泛的方案来解释与公平相关的品质。我们试图将可能的算法选择及其预期效果告知开发者和用户。总的来说，这将有效地支持具有保证性能水平的人工智能管道的发展。将使用三个用例（人力资源自动化、金融技术和广告）来评估我们方法的有效性。

In this proposal, we address the matter of transparency and explainability of AI using approaches inspired by control theory. Notably, we consider a comprehensive and flexible certification of properties of AI pipelines, certain closed-loops and more complicated interconnections. At one extreme, one could consider risk averse a priori guarantees via hard constraints on certain bias measures in the training process. At the other extreme, one could consider nuanced communication of the exact tradeoffs involved in AI pipeline choices and their effect on industrial and bias outcomes, post hoc. Both extremes offer little in terms of optimizing the pipeline and inflexibility in explaining the pipeline’sfairness-related qualities. Seeking the middle-ground, we suggest a priori certification of fairnessrelated qualities in AI pipelines via modular compositions of pre-processing, training, inference, and post-processing steps with certain properties. Furthermore, we present an extensive programme in explainability of fairness-related qualities. We seek to inform both the developer and the user thoroughly in regards to the possible algorithmic choices and their expected effects. Overall, this will effectively support the development of AI pipelines with guaranteed levels of performance, explained clearly. Three use cases (in Human Resources automation, Financial Technology, and Advertising) will be used to assess the effectiveness of our approaches.