S Luan, C Hua, Q Lu, J Zhu, M Zhao… - Advances in neural …, 2022 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While …
X Li, R Zhu, Y Cheng, C Shan, S Luo… - International …, 2022 - proceedings.mlr.press
We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with …
D Lim, F Hohne, X Li, SL Huang… - Advances in …, 2021 - proceedings.neurips.cc
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph …
Cellular sheaves equip graphs with a``geometrical''structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph …
Node classification is a classical graph representation learning task on which Graph Neural Networks (GNNs) have recently achieved strong results. However, it is often believed that …
Abstract Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, many existing GNN models have implicitly assumed …
Abstract Recent studies on Graph Neural Networks (GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both …
Y Zhu, Y Xu, Q Liu, S Wu - arXiv preprint arXiv:2109.01116, 2021 - arxiv.org
Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been …
Abstract Graph Neural Networks (GNNs) are widely used for analyzing graph-structured data. Most GNN methods are highly sensitive to the quality of graph structures and usually …