MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks

CMW-Net: an adaptive robust algorithm for sample selection and label correction

“…Inspired by this weighting-function-imposing methodology learning [ 5 ] for the competition, a critical extension is to simulate the methodology of how to set other hyperparameters in machine learning, e.g. learning rate [ 10 ], pseudo label [ 11 ], loss function [ 12 ], etc. This new learning manner provides valuable insights for machine learning automation and meta-learning [ 4 ].…”