FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs

Forum topic · 小凯 · 2026-08-27

Summary

FedV-KGQA is a federated framework for multi-hop question answering over knowledge graphs that are vertically partitioned across organizations due to governance and data sovereignty constraints. Organizations share entities but own disjoint relation sets. The approach combines local graph enrichment with knowledge graph embeddings so that raw triples and relation parameters never leave each silo, establishing a structural data boundary without centralized graph access. A topic entity anchoring mechanism grounds questions in the correct graph neighborhood without runtime cross-silo communication. Evaluated on three benchmarks across 12 model configurations, FedV-KGQA achieves performance close to centralized baselines, generalizes to 3-hop reasoning, and is robust to embedding perturbations. Paper by Md Saikat Islam Khan Bappy and Oshani Seneviratne, arXiv:2608.24846.

Overview

Field: AI Authors: Md Saikat Islam Khan Bappy, Oshani Seneviratne Published: 2026-08-25 arXiv: 2608.24846

Abstract

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 cross-silo communication.

Key Results

Evaluated on three benchmarks with 12 model configurations.
FedV-KGQA achieves strong performance, approaching centralized baselines.
Generalizes to 3-hop reasoning.
Robust to embedding perturbations.

---

*Auto-collected on 2026-08-27*