Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features Lars Henry Berge Olsen Ingrid Kristine Glad Martin Jullum Kjersti Aas Publication details Journal: Journal of machine learning research, vol. 23, p. 1–51–50, 2022 International Standard Numbers: Printed: 1532-4435 Electronic: 1533-7928 Links: ARKIV: http://hdl.handle.net/10852/97792 FULLTEKST: www.jmlr.org/papers/volume23/21-1413/21-1413.pdf Lars Henry Berge Olsen Research Scientist Martin Jullum Senior Research Scientist Kjersti Aas Research Director SAMBA You are here: Home Publications Scientific article Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features