A bidirectional reasoning approach for blood glucose control via invertible neural networks

Despite the profound advancements that deep learning models have achieved across a multitude of domains, their propensity to learn spurious correlations significantly impedes their applicability to tasks necessitating causal and counterfactual reasoning.

In this paper, we propose a Bidirectional Neural Network, which innovatively consolidates forward causal reasoning with inverse counterfactual reasoning into a cohesive framework. This integration is facilitated through the implementation of multi-stacked affine coupling layers, which ensure the network's invertibility, thereby enabling bidirectional reasoning capabilities within a singular architectural construct. To augment the network's trainability and to ensure the bidirectional differentiability of the parameters, we introduce an orthogonal weight normalization technique. Additionally, the counterfactual reasoning capacity of the Bidirectional Neural Network is embedded within the policy function of reinforcement learning, thereby effectively addressing the challenges associated with reward sparsity in the blood glucose control scenario.

We evaluate our framework on two pivotal tasks: causal-based blood glucose forecasting and counterfactual-based blood glucose control. The empirical results affirm that our model not only exemplifies enhanced generalization in causal reasoning but also significantly surpasses comparative models in handling out-of-distribution data. Furthermore, in blood glucose control tasks, the integration of counterfactual reasoning markedly improves decision efficacy, sample efficiency, and convergence velocity.

It is our expectation that the Bidirectional Neural Network will pave novel pathways in the exploration of causal and counterfactual reasoning, thus providing groundbreaking methods for complex decision-making processes. Code is available at https://github.com/HITshenrj/BNN.