Work

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

Year: 2026
Type: article
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.
Source: Mathematics
Language: English
Open Access status: gold
Estimated APC paid: $3,137
OpenAlex ID: W7235583435
FWCI:
Cites: 100
Cited by:
Related to: 10