aiqbench analysis
FedV-KGQA demonstrates that multi-hop question answering over vertically partitioned knowledge graphs can achieve near-centralized accuracy without sharing raw triples or relation embeddings. The research highlights that architectural choices like entity anchoring and local enrichment are more critical than specific embedding models, offering practical design lessons for privacy-preserving AI systems. This work advances the field by providing an interactive prototype that validates these findings on real inference pipelines.
FedV-KGQA in Practice: Design Lessons and an Interactive Prototype
arXiv:2609.13661v1 Announce Type: new Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR)
arXiv:2609.13661 [cs.AI]
(or arXiv:2609.13661v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.13661 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 286 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
Claude Code’s Next Era — Thariq Shihipar, Anthropic
Latent Space · Sep 29, 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026