Embedding static graphs in low-dimensional vector spaces plays a key role in network
analytics and inference, supporting applications like node classification, link prediction, and …

Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-
dimensional spaces according to specific tasks. Up to now, there have been several surveys …

Abstract We present the Temporal Graph Benchmark (TGB), a collection of challenging and
diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine …

Understanding crowd motion dynamics is critical to real-world applications, eg, surveillance
systems and autonomous driving. This is challenging because it requires effectively …

Learning node representations in graphs is important for many applications such as link
prediction, node classification, and community detection. Existing graph representation …

The dominant paradigm for relation prediction in knowledge graphs involves learning and
operating on latent representations (ie, embeddings) of entities and relations. However …

Temporal networks serve as abstractions of many real-world dynamic systems. These
networks typically evolve according to certain laws, such as the law of triadic closure, which …

Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities
by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …

Dynamic networks are used in a wide range of fields, including social network analysis,
recommender systems and epidemiology. Representing complex networks as structures …

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …