Many datasets are underspecified: there exist multiple equally viable solutions to a given task. Underspecification can be problematic for methods that learn a single hypothesis because different functions that achieve low training loss can focus on different predictive features and thus produce widely varying predictions on out-of-distribution data. We propose DivDis, a simple two-stage framework that first learns a diverse collection of hypotheses for a task by leveraging unlabeled data from the test distribution. We then disambiguate by selecting one of the discovered hypotheses using minimal additional supervision, in the form of additional labels or inspection of function visualization. We demonstrate the ability of DivDis to find hypotheses that use robust features in image classification and natural language processing problems with underspecification.
翻译:许多数据集被描述得不够详细:对特定任务存在多种同样可行的解决办法。对于学习单一假设的方法来说,具体程度过低可能会有问题,因为实现低培训损失的不同功能可以侧重于不同的预测特征,从而产生对分配外数据的不同预测。我们提议DivDis,这是一个简单的两阶段框架,首先通过利用测试分布中未加标签的数据,为一项任务学习各种各样的假设。然后,我们通过使用最起码的额外监督,以额外标签或功能可视化检查的形式,选择一个被发现的假设,从而模糊不清。我们证明DivDis有能力找到在图像分类中使用稳健特征的假说,并找出具体不足的自然语言处理问题。