New Frontiers in Graph Neural Networks: Emerging Architectures and Training Paradigms

This conference explores the latest advancements in Graph Neural Networks, focusing on novel architectures and scalable training methodologies that address complex relational data challenges. Designed for researchers, data scientists, and industry practitioners, the event provides a collaborative platform to bridge the gap between theoretical breakthroughs and practical applications. Participants will engage with cutting-edge research that is defining the next generation of geometric deep learning and graph representation models.

We invite original research contributions addressing novel graph neural network architectures, efficient training paradigms, and real-world applications of graph-based learning. Submissions exploring theoretical foundations, scalability improvements, or interdisciplinary deployments in fields such as bioinformatics and social network analysis are particularly encouraged.