Robust Deep Ordinal Regression Under Label Noise
This addresses label noise in ordinal regression for real-world applications, representing an incremental advance as it adapts existing loss functions to handle noise.
The paper tackles the problem of label noise in ordinal regression by proposing a theoretically grounded deep learning approach that is robust to label noise and rank consistent, showing empirical verification on real data.
The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account. We propose a theoretically grounded approach for class conditional label noise in ordinal regression problems. We present a deep learning implementation of two commonly used loss functions for ordinal regression that is both - 1) robust to label noise, and 2) rank consistent for a good ranking rule. We verify these properties of the algorithm empirically and show robustness to label noise on real data and rank consistency. To the best of our knowledge, this is the first approach for robust ordinal regression models.