Slides are available here.
[1] V. Balayan, P. Saleiro, C. Belém, L. Krippahl, and P. Bizarro, “Teaching the machine to explain itself using domain knowledge,” in NeurIPS 2020 Workshop on Human And Model in the Loop Evaluation and Training Strategies, 2020. Available: https://hamlets-workshop.github.io/schedule/
[2] S. Jesus, C. Belém, V. Balayan, J. Bento, P. Saleiro, P. Bizarro, and J.Gama, “How can i choose an explainer? an application-grounded evaluation of post-hoc explanations,” in Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21, Association for Computing Machinery, 2021, pp. 805–815. Available:https://doi.org/10.1145/3442188.3445941.
[3] C. Belém, V. Balayan, P. Saleiro, and P. Bizarro, “Weakly supervised multi-task learning for concept-based explainability,” in International Conference on Learning Representations 2021 Workshop on Weakly Supervised Learning, 2021. Available:https://weasul.github.io/accpapers/.
[4] J. Bento, P. Saleiro, A. F. Cruz, M. A. T. Figueiredo, and P. Bizarro, “TimeSHAP: Explaining Recurrent Models through Sequence Perturbations”, in Proc. of the 27th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, (KDD), 2021.