SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning

基于小语言模型（SLM）条件化分层关系路由的标签属性图学习

Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target.

标签属性图（Labeled Property Graphs）将关系结构与附着在节点和关系上的异构文本及分类属性相结合。传统的图神经网络通常将这些属性表示为静态特征向量，这限制了它们确定哪些语义证据应影响特定预测目标的传播信息的能力。

We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor’s structural state, node-property encoding, relationship-property encoding, and relationship type.

我们提出了“基于小语言模型（SLM）条件化分层关系路由”架构，该架构将一个小语言模型直接集成到图信息选择过程中。拓扑图神经网络（Topology GNN）提供了一个稳定的结构表示和预测锚点。对于每个目标节点，入射信息结合了邻居的结构状态、节点属性编码、关系属性编码以及关系类型。

A parameter-efficient SLM processes structured graph soft tokens and produces a target-conditioned routing query. This query first selects relevant messages within each relationship type and subsequently routes information across relation-level summaries. The resulting representation provides a bounded residual update to the topology anchor, preserving structural evidence while allowing contextual semantic information to modify the prediction.

参数高效的 SLM 处理结构化图软标记（soft tokens），并生成一个目标条件化的路由查询。该查询首先在每种关系类型内选择相关信息，随后在关系层级的摘要之间路由信息。由此产生的表示为拓扑锚点提供了有界的残差更新，在保留结构证据的同时，允许上下文语义信息对预测进行修正。

The architecture supports interpretable analysis at both the neighbor and relationship-type levels and provides a general mechanism for integrating language-derived semantics into property-rich graph learning.

该架构支持在邻居和关系类型两个层级上进行可解释性分析，并为将语言派生的语义集成到富属性图学习中提供了一种通用机制。