Supervisor

Suitable for

Abstract

Large-scale retrieval systems increasingly combine vector-based similarity search (for embedding-driven semantic retrieval) with graph-based indexes (for structured relationships and reasoning). However, efficiently joining results across these heterogeneous indexes remains an open research challenge.

This project aims to design and evaluate algorithms that perform joins between vector and graph indexes, implemented in C++ for high performance. The work is inspired by RDFox’s in-memory reasoning and query optimization techniques but extends them to operate in hybrid neural–symbolic settings.

 

This project presents the opportunity to work with one of the Computer Science department’s spinout companies, and success story, Oxford Semantic Technologies. As well as help candidates build their CV strong candidates will have the opportunity of summer internships with Oxford Semantics.

 

Background reading

 

Aidan Hogan et al. Knowledge Graphs. Synthesis Lectures on Data, Semantics, and Knowledge, Morgan & Claypool Publishers 2021, ISBN 978-3-031-00790-3, pp. 1-257

 

Heiko Paulheim.  Knowledge graph refinement: A survey of approaches and evaluation methods. Semantic Web 8(3): 489-508 (2017)

 

Jason Mohoney et al.  High-Throughput Vector Similarity Search in Knowledge Graphs. Proc. ACM Manag. Data 1(2): 197:1-197:25 (2023)