论文标题
部分可观测时空混沌系统的无模型预测
MaskTune: Mitigating Spurious Correlations by Forcing to Explore
论文作者
论文摘要
过度参数深度学习模型的基本挑战是学习有意义的数据表示，在下游任务上产生良好的性能，而无需过度拟合伪造的输入功能。这项工作提出了MaskTune，这是一种掩盖策略，可防止过度依赖伪造（或有限数量）的功能。 MaskTune迫使训练有素的模型通过掩盖先前发现的功能在单个时期的填充过程中探索新功能。与早期减轻快捷方式学习的方法不同，MaskTune不需要任何监督，例如在数据集中使用带注释的伪造功能或标签用于子组样品的标签。我们对有偏见的MNIST，Celeba，Waterbird和Imagennet-9L数据集的经验结果表明，MaskTune对通常遭受虚假相关性存在的任务有效。最后，我们表明，当应用于选择性分类（使用拒绝选项分类）任务时，MaskTune优于竞争方法的表现要优于竞争方法。 MaskTune的代码可从https://github.com/aliasgharkhani/masktune获得。
A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features. This work proposes MaskTune, a masking strategy that prevents over-reliance on spurious (or a limited number of) features. MaskTune forces the trained model to explore new features during a single epoch finetuning by masking previously discovered features. MaskTune, unlike earlier approaches for mitigating shortcut learning, does not require any supervision, such as annotating spurious features or labels for subgroup samples in a dataset. Our empirical results on biased MNIST, CelebA, Waterbirds, and ImagenNet-9L datasets show that MaskTune is effective on tasks that often suffer from the existence of spurious correlations. Finally, we show that MaskTune outperforms or achieves similar performance to the competing methods when applied to the selective classification (classification with rejection option) task. Code for MaskTune is available at https://github.com/aliasgharkhani/Masktune.
