Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints …
Abstract We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine …
J You, T Du, J Leskovec - Proceedings of the 28th ACM SIGKDD …, 2022 - dl.acm.org
Graph Neural Networks (GNNs) have been successfully applied to many real-world static graphs. However, the success of static graphs has not fully translated to dynamic graphs due …
Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of …
X Luo, H Wu, Z Wang, J Wang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
A d ynamically w eighted d irected n etwork (DWDN) is frequently encountered in various big data-related applications like a terminal interaction pattern analysis system (TIPAS) …
Abstract Graph Neural Networks (GNNs) have achieved promising performance on a wide range of graph-based tasks. Despite their success, one severe limitation of GNNs is the over …
There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight …
Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data. Such an ability …
Deep learning on graphs has become one of the hottest topics in machine learning. The book consists of four parts to best accommodate our readers with diverse backgrounds and …