The performance of machine learning models can significantly degrade under distribution shifts of the data. We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about the ``high-level" structure of the data with standard classifiers. Specifically, we introduce two-stage classifiers called memory classifiers. First, these identify prototypical data points -- memories -- to cluster the training data. This step is based on features designed with expert guidance; for instance, for image data they can be extracted using digital image processing algorithms. Then, within each cluster, we learn local classifiers based on finer discriminating features, via standard models like deep neural networks. We establish generalization bounds for memory classifiers. We illustrate in experiments that they can improve generalization and robustness to distribution shifts on image datasets. We show improvements which push beyond standard data augmentation techniques.
翻译:机器学习模型的性能在数据分布变化时会大大降低。 我们提出一种新的分类方法,通过将数据“高层次”结构的专家知识与标准分类器相结合,可以提高分布变化的稳健性。 具体地说, 我们引入了称为记忆分类器的两阶段分类器。 首先, 这些识别了原型数据点 -- -- 记忆 -- -- 以集中培训数据。 这个步骤基于专家指导设计的特点; 例如, 对于图像数据, 可以通过数字图像处理算法来提取。 然后, 在每组中, 我们通过深层神经网络等标准模型, 学习基于细微差别特征的本地分类器。 我们为记忆分类器设置了通用界限。 我们在实验中说明, 它们可以改进图像数据集的概括性和稳健性, 以分配变化。 我们展示了超越标准数据增强技术的改进。