Node features of graph neural networks (GNNs) tend to become more similar with the increase of the network depth. This effect is known as over-smoothing, which we …
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery …
G Li, M Müller, B Ghanem… - … conference on machine …, 2021 - proceedings.mlr.press
Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory …
There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight …
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 …
Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease …
The interdependence between nodes in graphs is key to improve class prediction on nodes, utilized in approaches like Label Probagation (LP) or in Graph Neural Networks (GNNs) …
X Liu, M Yan, L Deng, G Li, X Ye… - IEEE/CAA Journal of …, 2021 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although …
S Khoshraftar, A An - ACM Transactions on Intelligent Systems and …, 2024 - dl.acm.org
Graph representation learning has been a very active research area in recent years. The goal of graph representation learning is to generate graph representation vectors that …