Enhanced Meta Label Correction for Coping with Label Corruption
This addresses the challenge of handling real-world label noise in machine learning datasets, representing an incremental improvement over existing meta-label correction methods.
The paper tackles the problem of learning with noisy labels by proposing Enhanced Meta Label Correction (EMLC), which achieves state-of-the-art results on standard benchmarks, including a 1.52% improvement on the Clothing1M dataset while reducing training time per epoch by half.
Traditional methods for learning with the presence of noisy labels have successfully handled datasets with artificially injected noise but still fall short of adequately handling real-world noise. With the increasing use of meta-learning in the diverse fields of machine learning, researchers leveraged auxiliary small clean datasets to meta-correct the training labels. Nonetheless, existing meta-label correction approaches are not fully exploiting their potential. In this study, we propose an Enhanced Meta Label Correction approach abbreviated as EMLC for the learning with noisy labels (LNL) problem. We re-examine the meta-learning process and introduce faster and more accurate meta-gradient derivations. We propose a novel teacher architecture tailored explicitly to the LNL problem, equipped with novel training objectives. EMLC outperforms prior approaches and achieves state-of-the-art results in all standard benchmarks. Notably, EMLC enhances the previous art on the noisy real-world dataset Clothing1M by $1.52\%$ while requiring $\times 0.5$ the time per epoch and with much faster convergence of the meta-objective when compared to the baseline approach.