用于科学机器学习的可操作归因图
Actionable Attribution Maps for Scientific Machine Learning
摘要：
科学界越来越有兴趣利用深度学习的力量来解决各种领域的挑战。然而，尽管构建预测模型很有效，但由于深度神经网络的不透明性，从深度神经网络中提取可操作知识仍然存在根本性挑战。在这项工作中，我们提出了探索深度学习模型的行为的技术，通过在分析管道中注入特定领域的可操作概念作为可调的“旋钮”。通过将领域知识与生成建模相结合，我们不仅能够更好地理解这些黑盒模型的行为，而且还为科学家提供了可操作的见解，这些见解可能会导致根本性的发现。
英文摘要：
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in building predictive models, fundamental challenges exist in extracting actionable knowledge from the deep neural network due to their opaque nature. In this work, we propose techniques for exploring the behavior of deep learning models by injecting domain-specific actionable concepts as tunable ``knobs'' in the analysis pipeline. By incorporating the domain knowledge with generative modeling, we are not only able to better understand the behavior of these black-box models, but also provide scientists with actionable insights that can potentially lead to fundamental discoveries.
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。
