arXiv:2603.08731cs.NEcs.LG2026-03

让神经网络同时学习连接结构和同步相位,提升计算效率与稳定性。

Hebbian-Oscillatory Co-Learning

  • 通过振荡器同步信号控制突触结构调整,只在模式一致时更新连接。
  • 理论证明系统收敛到稳定状态,复杂度仅为O(n·k),远低于全连接网络。
  • 适合研究生物启发式稀疏神经网络的开发者,尤其关注动态结构优化者。

我们提出赫布-振荡协同学习(HOC-L),一种统一的双时间尺度动态框架,用于在生物启发的稀疏神经架构中实现结构可塑性与相位同步的联合学习。HOC-L结合了共振稀疏几何网络(RSGN)的双曲稀疏几何与赫布式动态稀疏机制,以及选择性同步注意力(SSA)的振荡器基注意力,用柯朗莫图型相位锁定动力学替代点积注意力。核心机制为同步门控可塑性:振荡器集合的宏观序参量$r(t)$调控赫布式结构更新,仅当相位相干性足够高、表明存在有意义的计算模式时才进行连接巩固。我们通过复合李雅普诺夫函数证明了联合系统的收敛性,并推导出明确的时间尺度分离界限。所得架构复杂度为$O(n \cdot k)$,且满足$k \ll n$,保持了两个父框架的稀疏性。数值模拟验证了理论预测,展示了涌现的簇对齐连接结构与单调下降的李雅普诺夫函数。

原文摘要 · Abstract (English)

We introduce Hebbian-Oscillatory Co-Learning (HOC-L), a unified two-timescale dynamical framework for joint structural plasticity and phase synchronization in bio-inspired sparse neural architectures. HOC-L couples two recent frameworks: the hyperbolic sparse geometry of Resonant Sparse Geometry Networks (RSGN), which employs Poincaré ball embeddings with Hebbian-driven dynamic sparsity, and the oscillator-based attention of Selective Synchronization Attention (SSA), which replaces dot-product attention with Kuramoto-type phase-locking dynamics. The key mechanism is synchronization-gated plasticity: the macroscopic order parameter $r(t)$ of the oscillator ensemble gates Hebbian structural updates, so that connectivity consolidation occurs only when sufficient phase coherence signals a meaningful computational pattern. We prove convergence of the joint system to a stable equilibrium via a composite Lyapunov function and derive explicit timescale separation bounds. The resulting architecture achieves $O(n \cdot k)$ complexity with $k \ll n$, preserving the sparsity of both parent frameworks. Numerical simulations confirm the theoretical predictions, demonstrating emergent cluster-aligned connectivity and monotonic Lyapunov decrease.

神经网络稀疏性同步可塑性

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。