Towards Learning and Explaining Indirect Causal Effects in Neural Networks
Towards Learning and Explaining Indirect Causal Effects in Neural Networks
Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models. By virtue of NN architectures, previous approaches consider only direct and total causal effects assuming independence among input variables. We view an NN as a structural causal model (SCM) and extend our …