Laura Rieger, Chandan Singh, W. James Murdoch, Bin Yu. Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Volume 119 of Proceedings of Machine Learning Research, pages 8116-8126, PMLR, 2020. [doi]
Abstract is missing.