Neural Bayesian Network Understudy
This work addresses the challenge of making clinical decision-making models more interpretable and causally aware, though it is incremental as it presents initial steps in this direction.
The paper tackles the problem of combining the causal knowledge of Bayesian Networks with the ability of neural networks to handle unstructured data, by training a neural network to output conditional probabilities and encode independence relations from causal structure, achieving a model that approximates the probabilistic and causal properties of a Bayesian Network in a proof-of-concept setting.
Bayesian Networks may be appealing for clinical decision-making due to their inclusion of causal knowledge, but their practical adoption remains limited as a result of their inability to deal with unstructured data. While neural networks do not have this limitation, they are not interpretable and are inherently unable to deal with causal structure in the input space. Our goal is to build neural networks that combine the advantages of both approaches. Motivated by the perspective to inject causal knowledge while training such neural networks, this work presents initial steps in that direction. We demonstrate how a neural network can be trained to output conditional probabilities, providing approximately the same functionality as a Bayesian Network. Additionally, we propose two training strategies that allow encoding the independence relations inferred from a given causal structure into the neural network. We present initial results in a proof-of-concept setting, showing that the neural model acts as an understudy to its Bayesian Network counterpart, approximating its probabilistic and causal properties.