Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from over-parameterization, complicating interpretation and raising uncertainty issues. Bayesian neural networks (BNNs) address the latter by representing weights as probability distributions, allowing for predictive uncertainty evaluation. Latent binary Bayesian neural networks (LBBNNs) further handle structural uncertainty and sparsify models by removing redundant weights. This article advances LBBNNs by enabling covariates to skip to any succeeding layer or be excluded, simplifying networks and clarifying input impacts on predictions. Ultimately, a linear model or even a constant can be found to be optimal for a specific problem at hand. Furthermore, the input-skip LBBNN approach reduces network density significantly compared to standard LBBNNs, achieving over 99% reduction for small networks and over 99.9% for larger ones, while still maintaining high predictive accuracy and uncertainty measurement. For example, on MNIST, we reached 97% accuracy and great calibration with just 935 weights, reaching state-of-the-art for compression of neural networks. Furthermore, the proposed method accurately identifies the true covariates and adjusts for system non-linearity. The main contribution is the introduction of active paths, enhancing directly designed global and local explanations within the LBBNN framework, that have theoretical guarantees and do not require post hoc external tools for explanations.

@article{høyheim2025_2503.10496,
  title={ Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks },
  author={ Eirik Høyheim and Lars Skaaret-Lund and Solve Sæbø and Aliaksandr Hubin },
  journal={arXiv preprint arXiv:2503.10496},
  year={ 2025 }
}