Neuromorphic Knowledge Representation: SNN-Based Relational Inference and Explainability in Knowledge Graphs

Gaganpreet Jhajj, Jerry Ryan David Gustafson, Raymond Morland, Carlos Enrique Gutierrez, Michael Pin Chuan Lin, M. Ali Akber Dewan, Fuhua Lin

Research output: Chapter in Book/Report/Conference proceedingPublished Conference contributionpeer-review

Abstract

This paper explores a neuromorphic approach to semantic knowledge representation using spiking neural networks (SNNs) for relational inference within knowledge graphs (KGs). While traditional KG models often rely on dense embeddings that lack interpretability, SNNs offer a biologically inspired alternative by encoding relationships through discrete, event-driven spikes. We evaluate three architectures—LIF-Base, RecurrentSNN, and LiquidSNN—on a dataset of 54 computer science-related KG triplets. Performance is assessed using relationship classification accuracy, temporal and spatial stability, and spike variability. Results show that relationship types produce distinct spike activation patterns, with LiquidSNN achieving the highest accuracy and spatial coherence. These findings support the potential of SNNs for structured, interpretable KG reasoning, with future applications in adaptive learning systems and explainable AI.

Original languageEnglish
Title of host publicationGenerative Systems and Intelligent Tutoring Systems - 21st International Conference, ITS 2025, Proceedings
EditorsSabine Graf, Angelos Markos
Pages159-165
Number of pages7
DOIs
Publication statusPublished - 2026
Event21st International Conference on Intelligent Tutoring Systems, ITS 2025 - Alexandroupolis, Greece
Duration: 2 Jun. 20256 Jun. 2025

Publication series

NameLecture Notes in Computer Science
Volume15724 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference21st International Conference on Intelligent Tutoring Systems, ITS 2025
Country/TerritoryGreece
CityAlexandroupolis
Period2/06/256/06/25

Keywords

  • Explainability and Interpretability
  • Knowledge Graphs (KGs)
  • Neuromorphic Computing
  • Spiking Neural Networks (SNNs)

Fingerprint

Dive into the research topics of 'Neuromorphic Knowledge Representation: SNN-Based Relational Inference and Explainability in Knowledge Graphs'. Together they form a unique fingerprint.

Cite this