研究人员推出了一种新颖的声明式查询语言——神经关系程序（NRPs），旨在统一结构化数据上的关系推理与神经计算。NRPs 扩展了 Datalog 风格的规则，以整合数值向量嵌入，从而在一个单一框架内实现关系逻辑和可学习神经组件的交织。这种方法使 NRPs 能够同时作为可训练的查询计划和关系结构化的神经架构，为关系数据库上的神经计算提供了一种通用方法。 AI
影响 该框架能够为结构化数据分析带来更复杂和更集成的 AI 模型。
排序理由 该集群包含一篇研究论文，详细介绍了用于结构化数据查询和神经计算的新形式化方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.11946v1 Announce Type: cross Abstract: The conventional approach to deep learning over relational databases applies neural models, such as Graph Neural Networks (GNNs), to a graph representation of the database. Recent approaches instead operate on databases directly, …
The conventional approach to deep learning over relational databases applies neural models, such as Graph Neural Networks (GNNs), to a graph representation of the database. Recent approaches instead operate on databases directly, associating tuples with embeddings and extending q…
The conventional approach to deep learning over relational databases applies neural models, such as Graph Neural Networks (GNNs), to a graph representation of the database. Recent approaches instead operate on databases directly, associating tuples with embeddings and extending q…