Learning Fast Sample Re-weighting Without Reward Data
This work addresses data bias issues in machine learning, offering a more efficient and broadly applicable solution for practitioners, though it is incremental as it builds on existing learning-based re-weighting frameworks.
The paper tackles the problem of data biases like imbalanced and corrupted labels by proposing a fast sample re-weighting method that eliminates the need for additional reward data and reduces computational costs, achieving competitive results in label noise robustness and long-tailed recognition with improved training efficiency.
Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels. Recent methods develop learning-based algorithms to learn sample re-weighting strategies jointly with model training based on the frameworks of reinforcement learning and meta learning. However, depending on additional unbiased reward data is limiting their general applicability. Furthermore, existing learning-based sample re-weighting methods require nested optimizations of models and weighting parameters, which requires expensive second-order computation. This paper addresses these two problems and presents a novel learning-based fast sample re-weighting (FSR) method that does not require additional reward data. The method is based on two key ideas: learning from history to build proxy reward data and feature sharing to reduce the optimization cost. Our experiments show the proposed method achieves competitive results compared to state of the arts on label noise robustness and long-tailed recognition, and does so while achieving significantly improved training efficiency. The source code is publicly available at https://github.com/google-research/google-research/tree/master/ieg.