Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.03376 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909378919006208 |
|---|---|
| author | Wang, Zerui Liu, Yan Huang, Jun |
| author_facet | Wang, Zerui Liu, Yan Huang, Jun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03376 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services Wang, Zerui Liu, Yan Huang, Jun Distributed, Parallel, and Cluster Computing Artificial Intelligence Networking and Internet Architecture 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. |
| title | An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2411.03376 |