论文标题
迈向机器引导的人类发起的解释性互动学习
Toward Machine-Guided, Human-Initiated Explanatory Interactive Learning
论文作者
论文摘要
最近的工作证明了将本地解释与积极学习的前景，以理解和监督黑盒模型。在这里，我们表明，在特定条件下，这些算法可能会歪曲所学模型的质量。原因是机器通过预测和解释查询实例的标签来说明其信念：如果机器没有意识到自己的错误，它可能最终会选择人为地表现良好的查询。这使机器向用户呈现的“叙述”有偏见。我们通过引入解释性指导学习来解决这种叙事偏见，这是一种新颖的互动学习策略，其中：i）主管负责选择查询实例，而II）II）机器使用了全球解释以说明其整体说明并指导主管来选择挑战性的挑战性，并指导主管。该策略保留了解释性相互作用的关键优势，同时避免了叙事偏见，并在样本复杂性方面与积极学习有利。最初的基于聚类的原型的经验评估突出了我们方法的希望。
Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of the model being learned. The reason is that the machine illustrates its beliefs by predicting and explaining the labels of the query instances: if the machine is unaware of its own mistakes, it may end up choosing queries on which it performs artificially well. This biases the "narrative" presented by the machine to the user.We address this narrative bias by introducing explanatory guided learning, a novel interactive learning strategy in which: i) the supervisor is in charge of choosing the query instances, while ii) the machine uses global explanations to illustrate its overall behavior and to guide the supervisor toward choosing challenging, informative instances. This strategy retains the key advantages of explanatory interaction while avoiding narrative bias and compares favorably to active learning in terms of sample complexity. An initial empirical evaluation with a clustering-based prototype highlights the promise of our approach.
