He Cheng
  • Bio
  • Papers
  • Projects
  • Talks
  • News
  • Services
  • Experience
  • CV

Efficient and Scalable Retrieval in Knowledge Graphs: From Single-Graph to Partitioned Multi-Graph Approaches

Lightning talk at AMIA 2025 NLP Workshop on scalable knowledge graph retrieval.
Author

He Cheng

Published

November 16, 2025

Event: AMIA 2025 Annual Symposium — NLP Workshop (Lightning Talk)
Location: Atlanta, Georgia, USA

Abstract

This lightning talk introduces LogosKG, a framework for efficient and scalable multi-hop knowledge graph retrieval. The approach leverages sparse incidence factorizations for single-graph retrieval and extends to partitioned multi-graph designs with degree-aware routing, caching, and distributed execution. Applications in large-scale biomedical reasoning and LLM integration are discussed.

AMIA

 

© 2026 He Cheng