Compositional Function Networks: A High-Performance Alternative to Deep Neural Networks with Built-in Interpretability
This addresses the need for transparent models in high-stakes domains like healthcare or finance, offering a novel alternative to existing interpretable methods.
The paper tackled the problem of black-box deep neural networks by introducing Compositional Function Networks (CFNs), which achieve competitive performance (e.g., 96.24% accuracy on CIFAR-10) while providing inherent interpretability through composed mathematical functions.
Deep Neural Networks (DNNs) deliver impressive performance but their black-box nature limits deployment in high-stakes domains requiring transparency. We introduce Compositional Function Networks (CFNs), a novel framework that builds inherently interpretable models by composing elementary mathematical functions with clear semantics. Unlike existing interpretable approaches that are limited to simple additive structures, CFNs support diverse compositional patterns -- sequential, parallel, and conditional -- enabling complex feature interactions while maintaining transparency. A key innovation is that CFNs are fully differentiable, allowing efficient training through standard gradient descent. We demonstrate CFNs' versatility across multiple domains, from symbolic regression to image classification with deep hierarchical networks. Our empirical evaluation shows CFNs achieve competitive performance against black-box models (96.24% accuracy on CIFAR-10) while outperforming state-of-the-art interpretable models like Explainable Boosting Machines. By combining the hierarchical expressiveness and efficient training of deep learning with the intrinsic interpretability of well-defined mathematical functions, CFNs offer a powerful framework for applications where both performance and accountability are paramount.