发表机构
Rensselaer Polytechnic Institute（伦斯勒理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对垂直分区知识图谱的多跳问答问题，提出FedV-KGQA框架，通过本地图谱丰富、知识图谱嵌入及主题实体锚定机制实现高效推理，性能接近集中式系统且鲁棒性良好。
AI 中文摘要
由于治理和数据主权限制，知识图谱问答所需的真实数据常分布在不同机构中。集中式系统无法在所需事实被拆分至垂直分区数据孤岛时回答多跳问题。本文提出FedV-KGQA框架，用于知识图谱多跳推理，其中各机构共享实体但拥有不相交的关系集。该方法结合本地图谱丰富与知识图谱嵌入，确保原始三元组和关系参数不离开任一数据孤岛，建立无需集中式图谱访问的结构性数据边界；还引入主题实体锚定机制，使问题锚定至正确图谱邻域，无需运行时跨孤岛通信。在三个基准上评估12种模型配置，结果显示FedV-KGQA表现强劲，性能接近集中式系统，可泛化至3跳推理，且对嵌入扰动具有鲁棒性。
英文摘要
Real-world data for knowledge graph question answering is often distributed across different organizations due to governance and data sovereignty constraints. While centralized systems exist, they cannot answer multi-hop questions when the required facts are split across vertically partitioned silos. In this paper, we propose FedV-KGQA, a framework for multi-hop reasoning over knowledge graphs in which organizations share entities but own disjoint sets of relations. Our approach combines local graph enrichment and knowledge graph embeddings to ensure raw triples and relation parameters never leave each silo, establishing a structural data boundary without requiring centralized graph access. We further introduce a topic entity anchoring mechanism that grounds questions in the correct graph neighborhood without any runtime inter-silo communication. We evaluate 12 model configurations across three benchmarks and show that FedV-KGQA performs strongly, remains close to centralized performance, generalizes to 3-hop reasoning, and is robust to embedding perturbations.
CommentsAccepted at ISWC 2026 (Research Track). To appear in the Proceedings of the 25th International Semantic Web Conference
