Rank-N-Contrast: Learning Continuous Representations for Regression
This addresses a fundamental limitation in regression tasks for fields like computer vision and healthcare, offering a novel approach to representation learning.
The paper tackles the problem of fragmented representations in deep regression models by proposing Rank-N-Contrast (RNC), a framework that learns continuous representations based on target rankings, resulting in state-of-the-art performance across five real-world datasets with improved robustness, efficiency, and generalization.
Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of sample orders, inducing suboptimal results across a wide range of regression tasks. To fill the gap, we propose Rank-N-Contrast (RNC), a framework that learns continuous representations for regression by contrasting samples against each other based on their rankings in the target space. We demonstrate, theoretically and empirically, that RNC guarantees the desired order of learned representations in accordance with the target orders, enjoying not only better performance but also significantly improved robustness, efficiency, and generalization. Extensive experiments using five real-world regression datasets that span computer vision, human-computer interaction, and healthcare verify that RNC achieves state-of-the-art performance, highlighting its intriguing properties including better data efficiency, robustness to spurious targets and data corruptions, and generalization to distribution shifts. Code is available at: https://github.com/kaiwenzha/Rank-N-Contrast.