让布尔网络可扩展互联，保持高效与小模型。
Scalable Interconnect Learning in Boolean Networks
- 设计可训练的固定参数互联结构，支持更宽输入。
- 通过逻辑等价剪枝和数据驱动剪枝，压缩模型且不损失精度。
- 适合资源受限设备上的高效推理部署。
可学习的可微分布尔逻辑网络（DBNs）已在资源受限硬件上实现高效推理。本文通过引入一个参数量恒定的可训练、可微分互联结构，使DBNs能够扩展到比以往可学习互联设计更宽的层，同时保持其优异的准确性。为进一步减小模型规模，提出两种互补的剪枝策略：基于SAT的逻辑等价性剪枝，在不影响性能的前提下移除冗余门；以及基于相似性的数据驱动剪枝，优于传统的基于幅度的贪婪基线，提供更优的压缩-精度权衡。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。