Scalable Interconnect Learning in Boolean Networks

Learned Differentiable Boolean Logic Networks (DBNs) already deliver efficient inference on resource-constrained hardware. We extend them with a trainable, differentiable interconnect whose parameter count remains constant as input width grows, allowing DBNs to scale to far wider layers than earlier learnable-interconnect designs while preserving their advantageous accuracy. To further reduce model size, we propose two complementary pruning stages: an SAT-based logic equivalence pass that removes redundant gates without affecting performance, and a similarity-based, data-driven pass that outperforms a magnitude-style greedy baseline and offers a superior compression-accuracy trade-off.

@article{kresse2025_2507.02585,
  title={ Scalable Interconnect Learning in Boolean Networks },
  author={ Fabian Kresse and Emily Yu and Christoph H. Lampert },
  journal={arXiv preprint arXiv:2507.02585},
  year={ 2025 }
}