No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
This work is significant for practitioners deploying models in safety-critical applications like medicine, where consistent performance across all data subgroups is crucial, even when those subgroups are not explicitly labeled.
The paper addresses hidden stratification in classification tasks, where models trained on coarse-grained labels perform inconsistently across finer-grained subclasses. The authors propose GEORGE, a method that estimates unknown subclass labels using feature space separability and then applies distributionally robust optimization. This approach improves worst-case subclass accuracy by up to 22 percentage points.
In real-world classification tasks, each class often comprises multiple finer-grained "subclasses." As the subclass labels are frequently unavailable, models trained using only the coarser-grained class labels often exhibit highly variable performance across different subclasses. This phenomenon, known as hidden stratification, has important consequences for models deployed in safety-critical applications such as medicine. We propose GEORGE, a method to both measure and mitigate hidden stratification even when subclass labels are unknown. We first observe that unlabeled subclasses are often separable in the feature space of deep neural networks, and exploit this fact to estimate subclass labels for the training data via clustering techniques. We then use these approximate subclass labels as a form of noisy supervision in a distributionally robust optimization objective. We theoretically characterize the performance of GEORGE in terms of the worst-case generalization error across any subclass. We empirically validate GEORGE on a mix of real-world and benchmark image classification datasets, and show that our approach boosts worst-case subclass accuracy by up to 22 percentage points compared to standard training techniques, without requiring any prior information about the subclasses.