A Survey on Graph Neural Networks

Graph Neural Networks (GNNs) have emerged as a fundamental class of models for analyzing graph-structured data, with broad applications spanning social networks, computational neuroscience, and intelligent transportation systems. In contrast to Euclidean data, graphs pose distinctive challenges due to their irregular topology, permutation invariance, and multi-scale nature. GNNs address these issues through message-passing mechanisms that facilitate efficient representation learning by propagating and aggregating node-level information across the network. This survey offers a timely and systematic review of recent progress in GNNs, with a particular focus on methodological advances since 2022. We provide a structured synthesis of the rapidly expanding literature, categorizing and analyzing key innovations across architectural design, optimization strategies, and structural adaptations. The review also highlights impactful applications of GNNs in diverse domains and identifies critical open challenges in scalability, dynamic graph processing, interpretability, and integration with other artificial intelligence paradigms. We conclude by outlining promising research avenues to guide future developments in graph representation learning.