Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static)
graph-structured data. However, many real-world systems are dynamic in nature, since the …

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

Graph neural networks (GNNs) have emerged as a powerful tool for effectively mining and
learning from graph-structured data, with applications spanning numerous domains …

We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning.
DyGFormer is conceptually simple and only needs to learn from nodes' historical first-hop …

Temporal graphs are widely used to model dynamic systems with time-varying interactions.
In real-world scenarios, the underlying mechanisms of generating future interactions in …

Modeling the dynamics into graph neural networks (GNNs) contributes to the understanding
of evolution in dynamic graphs, which helps optimize temporal-spatial representations for …

Dynamic graph neural networks (DyGNNs) currently struggle with handling distribution shifts
that are inherent in dynamic graphs. Existing work on DyGNNs with out-of-distribution …

Temporal networks have been widely used to model real-world complex systems such as
financial systems and e-commerce systems. In a temporal network, the joint neighborhood of …

Numerous studies have been conducted to investigate the properties of large-scale
temporal graphs. Despite the ubiquity of these graphs in real-world scenarios, it's usually …

Discrimination against minority groups within the banking sector has long resulted in
unequal treatment in financial services. Recent works in the general machine learning …