FedV-KGQA 实践：设计经验与交互式原型
FedV-KGQA in Practice: Design Lessons and an Interactive Prototype
浏览论文内容
中文总结 AI 辅助
FedV-KGQA 在垂直划分的知识图谱上实现多跳问答，通过联邦融合恢复集中式准确率，并总结出锚定与丰富化优先、编码器选择依目标准确率而定等设计经验，同时提供可交互的原型系统。
中文摘要 AI 辅助
知识图谱问答通常假设单一系统能够访问整个图谱。然而在实践中，事实往往由多个组织持有，这些组织共享实体标识符，但各自拥有不相交的关系类型，因此没有任何单一方能观察到完整的推理链。本海报展示了 FedV-KGQA 在垂直划分图谱上进行多跳问答的实证研究结果。每个数据孤岛丰富其本地图谱，并基于自身三元组训练知识图谱嵌入。随后，服务器拼接各孤岛特有的实体视图，将投影后的问题锚定在主题实体上，并根据相似度对候选答案进行排序。原始三元组和关系嵌入从不离开数据孤岛。对 FedV-KGQA 实验进行相互比较得出三项结果。第一，联邦融合恢复了集中式准确率的大部分，而单一孤岛仅能恢复很少部分。第二，锚定和丰富化比嵌入模型的选择更为重要。第三，最廉价的编码器取决于目标准确率而非参数数量。本海报论文贡献了上述跨实验比较、从中总结的四条设计经验，以及一个交互式原型，该原型在已发布的检查点上对每个问题执行真实推理并追踪完整流水线。
英文摘要
Knowledge graph question answering usually assumes that one system can reach the whole graph. In practice, facts are often held by organizations that share entity identifiers but own disjoint relation types, so no single party sees a complete reasoning chain. This poster presents the empirical findings of FedV-KGQA on multi-hop question answering over such vertically partitioned graphs. Each silo enriches its local graph and trains a knowledge graph embedding on its own triples. A server then concatenates the silo-specific entity views, anchors the projected question at the topic entity, and ranks candidates by similarity. Raw triples and relation embeddings never leave a silo. Comparing the FedV-KGQA experiments with one another yields three results. First, federated fusion recovers most of the centralized accuracy, while a single silo recovers little. Second, anchoring and enrichment matter more than the choice of embedding model. Third, the cheapest encoder depends on the target accuracy rather than on parameter count. This poster paper contributes that cross-experiment comparison, four design lessons drawn from it, and an interactive prototype that runs real inference and traces the full pipeline, per question, on released checkpoints.
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。
