Interpretable Geometric Deep Learning via Learnable Randomness Injection
Interpretable Geometric Deep Learning via Learnable Randomness Injection
复制标题
DOI：
10.48550/arxiv.2210.16966
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Siqi Miao;Yunan Luo;Miaoyuan Liu;Pan Li
中科院分区：
文献类型：
--
作者：
Siqi Miao;Yunan Luo;Miaoyuan Liu;Pan Li
点云数据在科学领域中无处不在。最近，几何深度学习（GDL）已被广泛应用于解决此类数据的预测任务。然而，GDL模型往往是复杂的，很难解释，这给科学家谁是部署这些模型在科学分析和实验的关注。这项工作提出了一个通用的机制，可学习的随机注入（LRI），它允许建立固有的解释模型的基础上，一般GDL骨干。LRI诱导的模型一旦被训练，就可以检测点云数据中携带指示预测标签的信息的点。我们还提出了四个数据集从真实的科学应用，涵盖了高能物理和生物化学领域的LRI机制进行评估。与以前的事后解释方法相比，LRI检测到的点与具有实际科学意义的地面实况模式更好，更稳定。LRI基于信息瓶颈原理，因此LRI诱导的模型对训练和测试场景之间的分布变化也更鲁棒。我们的代码和数据集可以在\url{https：//github.com/Graph-COM/LRI}上找到。
Point cloud data is ubiquitous in scientific fields. Recently, geometric deep learning (GDL) has been widely applied to solve prediction tasks with such data. However, GDL models are often complicated and hardly interpretable, which poses concerns to scientists who are to deploy these models in scientific analysis and experiments. This work proposes a general mechanism, learnable randomness injection (LRI), which allows building inherently interpretable models based on general GDL backbones. LRI-induced models, once trained, can detect the points in the point cloud data that carry information indicative of the prediction label. We also propose four datasets from real scientific applications that cover the domains of high-energy physics and biochemistry to evaluate the LRI mechanism. Compared with previous post-hoc interpretation methods, the points detected by LRI align much better and stabler with the ground-truth patterns that have actual scientific meanings. LRI is grounded by the information bottleneck principle, and thus LRI-induced models are also more robust to distribution shifts between training and test scenarios. Our code and datasets are available at \url{https://github.com/Graph-COM/LRI}.