B Li, D Pi - Neural Computing and Applications, 2020 - Springer
Omnipresent network/graph data generally have the characteristics of nonlinearity, sparseness, dynamicity and heterogeneity, which bring numerous challenges to network …
Abstract Graph Neural Networks (GNNs) are limited in their expressive power, struggle with long-range interactions and lack a principled way to model higher-order structures. These …
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems. However, graphs alone cannot capture the multi-level …
M Zhang, P Li - Advances in Neural Information Processing …, 2021 - proceedings.neurips.cc
Graph neural network (GNN)'s success in graph classification is closely related to the Weisfeiler-Lehman (1-WL) algorithm. By iteratively aggregating neighboring node features …
While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the …
H Maron, H Ben-Hamu… - Advances in neural …, 2019 - proceedings.neurips.cc
Abstract Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressive power of graph neural networks (GNN). It was shown that the …
M Zhang, Y Chen - Advances in neural information …, 2018 - proceedings.neurips.cc
Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood …
Neural networks are typically designed to deal with data in tensor forms. In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure. Given a …
Mixup is an advanced data augmentation method for training neural network based image classifiers, which interpolates both features and labels of a pair of images to produce …