Recent Advances in Efficient and Scalable Graph Neural Networks | Chaitanya K. Joshi

An overview of papers on efficient Graph Neural Networks and scalable Graph Representation Learning for real-world applications. This article aims to provide an overview of key ideas on efficient Graph Neural Networks and scalable Graph Representation Learning. We will cover key developments in data preparation, GNN architectures, and learning paradigms that are enabling Graph Neural Networks to scale to real-world graphs and real-time applications. Graph Neural Networks are an emerging line of deep learning architectures that can build actionable representations of irregular data structures such as graphs, sets, and 3D point clouds. In recent years, GNNs have powered several impactful applications in fields ranging from social networks and recomendation systems to biomedical discovery and traffic forecasting. Building GNNs to handle real-world graph data poses several theoretical and engineering challenges, the most prominent among which are: Real-world networks can grow ginormously l

saved by

• Curtis Chong