Python code for influential instance estimation proposed in the following paper.
- S. Hara, A. Nitanda, T. Maehara, Data Cleansing for Models Trained with SGD. Advances in Neural Information Processing Systems 32 (NeurIPS'19), 2019.
experiment: This directory contains Python+PyTorch implementations used for the experiments in the paper.slide: This directory contains a slide describing how influential instances are estimated in the paper above.