{"ID":2898733,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.02585","arxiv_id":"2507.02585","title":"Scalable Interconnect Learning in Boolean Networks","abstract":"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.","short_abstract":"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-interconn...","url_abs":"https://arxiv.org/abs/2507.02585","url_pdf":"https://arxiv.org/pdf/2507.02585v2","authors":"[\"Fabian Kresse\",\"Emily Yu\",\"Christoph H. Lampert\"]","published":"2025-07-03T12:45:45Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.LO\"]","methods":"[]","has_code":false}