Brain-Inspired Graph Learning: From Neural Connectivity and Spiking Dynamics to Cognitive Plasticity

Graph learning provides a framework for modeling relational data, while brain-inspired approaches introduce principles of neural connectivity, neuronal dynamics, synaptic plasticity, and memory into graph-based computation. Existing studies span connectome-constrained modeling, spiking graph neural networks, local learning rules, and cognitive representations, but differ in their computational objectives and the evidence supporting their use in graph learning. This review examines these studies through four related dimensions: structure, dynamics, plasticity, and cognition. We first establish the theoretical foundations and distinguish brain-inspired computational mechanisms from the use of brain-derived graph data. We then analyze how neural connectivity principles shape graph organization and information propagation, how neuronal dynamics support temporal state processing, and how plasticity and cognitive mechanisms contribute to adaptation, memory, and relational reasoning. Representative studies are compared in terms of their computational mechanisms, application settings, and limitations, with attention to the distinction between direct graph-learning evidence and findings from neural or cognitive modeling. We further discuss the tasks, benchmark datasets, evaluation measures, and implementation costs relevant to assessing these approaches. Finally, we summarize unresolved issues in relating neural principles to graph computation, coordinating structural and temporal processes, maintaining knowledge under graph changes, and scaling spiking implementations. This review provides a mechanism-oriented account of current research and identifies the computational questions that remain open in brain-inspired graph learning.

Authors

Institutions

Publication Details

Journal
Mathematics
Published
2026-11-17
DOI
https://doi.org/10.3390/math14224228
Primary Topic
Advanced Graph Neural Networks
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Brain-Inspired Graph Learning: From Neural Connectivity and Spiking Dynamics to Cognitive Plasticity

Jing Zhang, Chunxiao Yin, Xinyue Zhou
Mathematics
Advanced Graph Neural Networks
article

Brain-Inspired Graph Learning: From Neural Connectivity and Spiking Dynamics to Cognitive Plasticity

Jing Zhang, Chunxiao Yin, Xinyue Zhou
article en

Abstract

Graph learning provides a framework for modeling relational data, while brain-inspired approaches introduce principles of neural connectivity, neuronal dynamics, synaptic plasticity, and memory into graph-based computation. Existing studies span connectome-constrained modeling, spiking graph neural networks, local learning rules, and cognitive representations, but differ in their computational objectives and the evidence supporting their use in graph learning. This review examines these studies through four related dimensions: structure, dynamics, plasticity, and cognition. We first establish the theoretical foundations and distinguish brain-inspired computational mechanisms from the use of brain-derived graph data. We then analyze how neural connectivity principles shape graph organization and information propagation, how neuronal dynamics support temporal state processing, and how plasticity and cognitive mechanisms contribute to adaptation, memory, and relational reasoning. Representative studies are compared in terms of their computational mechanisms, application settings, and limitations, with attention to the distinction between direct graph-learning evidence and findings from neural or cognitive modeling. We further discuss the tasks, benchmark datasets, evaluation measures, and implementation costs relevant to assessing these approaches. Finally, we summarize unresolved issues in relating neural principles to graph computation, coordinating structural and temporal processes, maintaining knowledge under graph changes, and scaling spiking implementations. This review provides a mechanism-oriented account of current research and identifies the computational questions that remain open in brain-inspired graph learning.

MathematicsVol. 14(22)
Southeast University (CN)
Advanced Graph Neural Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon