一种开放API架构，用于发现云AI服务的可信解释
An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
AI总结：
本文提出一种基于开放API的微服务架构，为云AI服务提供特征贡献解释，无需展开模型网络，可评估模型性能与XAI一致性指标，且架构云无关，数据增强能提升一致性。
摘要：
本文介绍了一种基于开放API的可解释人工智能（XAI）服务的设计，旨在为云AI服务提供特征贡献解释。云AI服务被广泛用于开发具有精确学习指标的领域特定应用。然而，底层云AI服务在模型如何产生预测方面仍然不透明。我们认为，XAI操作可以作为开放API访问，从而能够将XAI操作整合到云AI服务评估中。我们提出了一种使用微服务架构的设计，该架构在不展开云模型网络结构的情况下，为云AI服务提供特征贡献解释。我们还可以利用此架构评估模型性能和XAI一致性指标，以展示云AI服务的可信度。我们从操作管道中收集溯源数据，以实现XAI服务内的可重复性。此外，我们展示了针对领先云视觉AI服务的模型性能和XAI一致性指标的实验测试发现场景。结果证实，基于开放API的架构是云无关的。此外，数据增强导致云AI服务的XAI一致性指标有可衡量的改进。
英文摘要：
This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.
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。
