Group Robustness via Discounted Rank Upweighting
Abstract: Recent work has shown that standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on underrepresented groups due to the prevalence of spurious features. A predominant approach to tackle this group robustness problem minimizes the worst group error (akin to a {\it minimax} strategy) on the training data with the expectation that it will generalize well to unseen test data. However, this is often suboptimal, especially when the out-of-distribution (OOD) test data contains previously unseen groups. Inspired by ideas from the information retrieval and learning-to-rank literature, this paper first proposes to use Discounted Cumulative Gain (DCG) as a metric of model quality for facilitating better hyperparameter tuning and model selection. Being a ranking-based metric, DCG weights multiple poorly-performing groups (instead of considering just the group with the worst performance). As a natural next step, we build on our results to propose a ranking-based training method called \textbf{Discounted Rank Upweighting (DRU)} which differentially reweights a ranked list of poorly-performing groups in the training data to learn models that exhibit strong OOD performance on the test data. Results on several synthetic and real-world datasets highlight the superior generalization ability of our group-ranking-based (akin to {\it soft-minimax}) approach in selecting and learning models that are robust to group distributional shifts.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Matthew_J._Holland1
Submission Number: 1659
Loading