The topics include but not limited to: (a) Graph neural network (GNN); (b) Graph embedding; (c) Graph analysis community detection, graph/node classification, link prediction, node ranking, centrality); (d) Knowledge Graph (KG); (e) Temporal-spatial graphs; (f) Fairness, interpretability and explainability for graph learning; (g) Differentially private analysis of graphs; (h) Federated graph machine learning; (i) AutoML for graphs; (j) Various types of graphs (bipartite graph, multi-layer graphs, signed graphs, heterogeneous graphs); (k) large-scale graph visualization; (l) Applications of these technologies, such as recommender systems, point clouds, anomaly detection, text classification, image classification, sentiment analysis, question answering, emergency behaviors modeling and prediction, drug discovery, social influence prediction, traffic forecasting, neural machine translation, etc.