ExTuNe: Explaining Tuple Non-conformance
ExTuNe: Explaining Tuple Non-conformance
复制标题
ExTuNe：解释元组不一致性
DOI：
10.1145/3318464.3384694
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Sumit Gulwani
中科院分区：
文献类型：
--
作者：
Anna Fariha;A. Tiwari;Arjun Radhakrishna;Sumit Gulwani
在数据驱动的系统中，我们经常遇到机器学习模型的预测不可信的元组。这种不信任性的关键原因是相对于培训数据集的新元组不合格。为了检查一致性，我们介绍了一个新颖的数据不变性概念，该概念捕获了一组隐性约束，即数据集的所有元组都满足：如果违反数据不变性，则测试元组不合格。数据不变式建模多个属性之间的复杂关系；但是不要提供不合格的可解释解释。我们提出扩展，这是一种解释元组不合格原因的系统。基于因果关系的原则，Extune将责任分配给造成不符合的属性。关键的想法是观察在属性价值的干预下不变违规行为的变化。通过简单的接口，Extune根据其不合格的程度产生了测试元素的排名列表，并可以通过热图可视化元组级属性责任。 Extune进一步可视化属性责任，该责任在测试元组上汇总。我们证明了Extune如何检测和解释元组不合格，并帮助用户做出仔细的决定，以实现可信赖的机器学习。
In data-driven systems, we often encounter tuples on which the predictions of a machine-learned model are untrustworthy. A key cause of such untrustworthiness is non-conformance of a new tuple with respect to the training dataset. To check conformance, we introduce a novel concept of data invariant, which captures a set of implicit constraints that all tuples of a dataset satisfy: a test tuple is non-conforming if it violates the data invariants. Data invariants model complex relationships among multiple attributes; but do not provide interpretable explanations of non-conformance. We present ExTuNe, a system for Explaining causes of Tuple Non-conformance. Based on the principles of causality, ExTuNe assigns responsibility to the attributes for causing non-conformance. The key idea is to observe change in invariant violation under intervention on attribute-values. Through a simple interface, ExTuNe produces a ranked list of the test tuples based on their degree of non-conformance and visualizes tuple-level attribute responsibility for non-conformance through heat maps. ExTuNe further visualizes attribute responsibility, aggregated over the test tuples. We demonstrate how ExTuNe can detect and explain tuple non-conformance and assist the users to make careful decisions towards achieving trusted machine learning.