Reviews: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

This paper studies the problem of learning from biased training data (i.e. This covers notably the case of class imbalance and noisy label. The proposed meta-weight-net is an MLP with one hidden layer that learns a mapping from training loss of a sample to its weight. Minimizing the training objectives naturally leads us to focus more on samples that agree with the meat-knowledge. Theoretically it is shown that the algorithm converges to critical points of the loss under classical assumptions (but I am quite confused by the proof, see below).