arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.13265cs.LG
收藏

知识、规则及其嵌入:迈向神经符号JEPA的两条路径

Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA

Yongchao Huang, Hassan Raza

AI总结:

本文提出双向神经符号框架RiJEPA,通过能量约束和多模态双编码架构注入归纳偏置,重塑表示流形,实现几何逻辑盆地;并通过连续可微逻辑替代离散规则,实现连续规则发现,提升生成与推理能力。

摘要:

现代自监督预测架构在高维数据中擅长捕捉复杂统计相关性,但缺乏内化可验证人类逻辑的机制,易受虚假相关性和捷径学习影响。传统基于规则的推理系统提供严谨可解释的逻辑,但存在离散边界和NP难的组合爆炸问题。为弥合这一差距,我们提出以规则引导的联合嵌入预测架构(RiJEPA)为核心的双向神经符号框架。在第一方向,通过能量约束(EBC)和多模态双编码架构向JEPA训练注入结构归纳偏置,从根本上重塑表示流形,将任意统计相关性替换为几何上稳健的逻辑盆地。在第二方向,通过将严格离散的符号规则转化为连续可微逻辑,可以绕过传统组合搜索生成新规则。利用梯度引导的兰格瓦尔扩散在规则能量景观中,引入连续规则发现的新范式,实现无条件联合生成、条件前向推理和归纳推理以及边缘预测翻译。在合成拓扑模拟和高风险临床用例上的实证评估证实了我们方法的有效性。最终,该框架为稳健、生成和可解释的神经符号表示学习建立了强大基础。

英文摘要:

Modern self-supervised predictive architectures excel at capturing complex statistical correlations from high-dimensional data but lack mechanisms to internalize verifiable human logic, leaving them susceptible to spurious correlations and shortcut learning. Conversely, traditional rule-based inference systems offer rigorous, interpretable logic but suffer from discrete boundaries and NP-hard combinatorial explosion. To bridge this divide, we propose a bidirectional neuro-symbolic framework centered around Rule-informed Joint-Embedding Predictive Architectures (RiJEPA). In the first direction, we inject structured inductive biases into JEPA training via Energy-Based Constraints (EBC) and a multi-modal dual-encoder architecture. This fundamentally reshapes the representation manifold, replacing arbitrary statistical correlations with geometrically sound logical basins. In the second direction, we demonstrate that by relaxing rigid, discrete symbolic rules into a continuous, differentiable logic, we can bypass traditional combinatorial search for new rule generation. By leveraging gradient-guided Langevin diffusion within the rule energy landscape, we introduce novel paradigms for continuous rule discovery, which enable unconditional joint generation, conditional forward and abductive inference, and marginal predictive translation. Empirical evaluations on both synthetic topological simulations and a high-stakes clinical use case confirm the efficacy of our approach. Ultimately, this framework establishes a powerful foundation for robust, generative, and interpretable neuro-symbolic representation learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑