Learning to rectify for robust learning with noisy labels

•Our WarPI is the first probabilistic model to resolve label noise within the meta-learning scenario.•We design a powerful amortized meta-network to estimate the distribution of the rectifying vector from the input of labels and predicted vector.•WarPI can be directly integrated into the training of the prediction network, demonstrating favorable effectiveness to learn from noisy labels.•WarPI achieves the new state-of-the-art on four challenging benchmarks under variant noise types.