arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00491cs.AIcs.HC
收藏

EXMOS:通过多维度解释与数据配置实现解释性模型调控

EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations

KU Leuven(鲁汶大学);University of Glasgow(格拉斯哥大学);University of Maribor(马里博尔大学)

Aditya Bhattacharya, Simone Stumpf, Lucija Gosak, Gregor Stiglic, Katrien Verbert

AI总结:

本研究针对交互式机器学习系统中不同类型全局解释辅助医疗专家优化模型的有效性问题,通过定量与定性研究验证了数据中心与模型中心解释的混合融合方案效果最优,并给出解释驱动型系统的设计启示。

摘要:

交互式机器学习系统中的解释有助于调试和改进预测模型。然而,各类以模型为中心和以数据为中心的全局解释在协助领域专家发现并解决潜在数据问题以改进模型方面的有效性,仍有待探索。本研究针对支持医疗专家通过自动和手动数据配置优化模型的系统,探究了以数据为中心和以模型为中心的全局解释的作用。我们对医疗专家开展了定量研究(n=70)和定性研究(n=30),以探索不同解释对信任度、可理解性和模型改进的影响。结果表明,仅靠以模型为中心的全局解释不足以在数据配置过程中引导用户。虽然以数据为中心的解释提升了用户对配置后系统变化的理解,但两种解释类型的混合融合方案展现出最高的有效性。基于研究结果,我们还提出了构建有效的解释驱动型交互式机器学习系统的设计启示。

英文摘要:

Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric and data-centric explanations in aiding domain experts to detect and resolve potential data issues for model improvement remains unexplored. This research investigates the influence of data-centric and model-centric global explanations in systems that support healthcare experts in optimising models through automated and manual data configurations. We conducted quantitative (n=70) and qualitative (n=30) studies with healthcare experts to explore the impact of different explanations on trust, understandability and model improvement. Our results reveal the insufficiency of global model-centric explanations for guiding users during data configuration. Although data-centric explanations enhanced understanding of post-configuration system changes, a hybrid fusion of both explanation types demonstrated the highest effectiveness. Based on our study results, we also present design implications for effective explanation-driven interactive machine-learning systems.

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。

↑