Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of CNNs to graph-structured data, and neural message-passing approaches. These advances in graph neural networks and related techniques have led to new state-of-the-art results in numerous domains: chemical synthesis, 3D-vision, recommender systems, question answering, continuous control, self-driving and social network analysis. Building on the successes of three related workshops from last year (at ICML, ICLR and NeurIPS), the primary goal for this workshop is to facilitate community building, and support expansion of graph representation learning into more interdisciplinary projects with the natural and social sciences. With hundreds of new researchers beginning projects in this area, we hope to bring them together to consolidate this fast-growing area into a healthy and vibrant subfield. Especially, we aim to strongly promote novel and exciting applications of graph representation learning across the sciences, reflected in our choices of invited speakers.