Efficient Parallel Multi-Hop Reasoning: A Scalable Approach for Knowledge Graph Analysis

Multi-hop reasoning (MHR) is a process in artificial intelligence and natural language processing where a system needs to make multiple inferential steps to arrive at a conclusion or answer. In the context of knowledge graphs or databases, it involves traversing multiple linked entities and relation...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jesmin Jahan Tithi, Checconi, Fabio, Petrini, Fabrizio
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.06.2024
Subjects
Algorithms
Apexes
Artificial intelligence
Deep learning
Graph theory
Graphs
Harnesses
Knowledge bases (artificial intelligence)
Knowledge representation
Machine learning
Natural language processing
Reasoning
Task complexity
Online AccessGet full text

Cover

More Information
Summary:Multi-hop reasoning (MHR) is a process in artificial intelligence and natural language processing where a system needs to make multiple inferential steps to arrive at a conclusion or answer. In the context of knowledge graphs or databases, it involves traversing multiple linked entities and relationships to understand complex queries or perform tasks requiring a deeper understanding. Multi-hop reasoning is a critical function in various applications, including question answering, knowledge base completion, and link prediction. It has garnered significant interest in artificial intelligence, machine learning, and graph analytics. This paper focuses on optimizing MHR for time efficiency on large-scale graphs, diverging from the traditional emphasis on accuracy which is an orthogonal goal. We introduce a novel parallel algorithm that harnesses domain-specific learned embeddings to efficiently identify the top K paths between vertices in a knowledge graph to find the best answers to a three-hop query. Our contributions are: (1) We present a new parallel algorithm to enhance MHR performance, scalability and efficiency. (2) We demonstrate the algorithm's superior performance on leading-edge Intel and AMD architectures through empirical results. We showcase the algorithm's practicality through a case study on identifying academic affiliations of potential Turing Award laureates in Deep Learning, highlighting its capability to handle intricate entity relationships. This demonstrates the potential of our approach to enabling high-performance MHR, useful to navigate the growing complexity of modern knowledge graphs.
ISSN:2331-8422