Specformer: Spectral graph neural networks meet transformers

D Bo, C Shi, L Wang, R Liao - arxiv preprint arxiv:2303.01028, 2023‏ - arxiv.org
Spectral graph neural networks (GNNs) learn graph representations via spectral-domain
graph convolutions. However, most existing spectral graph filters are scalar-to-scalar …

Graph convolutional kernel machine versus graph convolutional networks

Z Wu, Z Zhang, J Fan - Advances in neural information …, 2023‏ - proceedings.neurips.cc
Graph convolutional networks (GCN) with one or two hidden layers have been widely used
in handling graph data that are prevalent in various disciplines. Many studies showed that …

Pc-conv: Unifying homophily and heterophily with two-fold filtering

B Li, E Pan, Z Kang - Proceedings of the AAAI conference on artificial …, 2024‏ - ojs.aaai.org
Recently, many carefully designed graph representation learning methods have achieved
impressive performance on either strong heterophilic or homophilic graphs, but not both …

Energy transformer

B Hoover, Y Liang, B Pham, R Panda… - Advances in neural …, 2023‏ - proceedings.neurips.cc
Our work combines aspects of three promising paradigms in machine learning, namely,
attention mechanism, energy-based models, and associative memory. Attention is the power …

A survey on spectral graph neural networks

D Bo, X Wang, Y Liu, Y Fang, Y Li, C Shi - arxiv preprint arxiv:2302.05631, 2023‏ - arxiv.org
Graph neural networks (GNNs) have attracted considerable attention from the research
community. It is well established that GNNs are usually roughly divided into spatial and …

Bridging the gap between spatial and spectral domains: A unified framework for graph neural networks

Z Chen, F Chen, L Zhang, T Ji, K Fu, L Zhao… - ACM Computing …, 2023‏ - dl.acm.org
Deep learning's performance has been extensively recognized recently. Graph neural
networks (GNNs) are designed to deal with graph-structural data that classical deep …

Towards effective and general graph unlearning via mutual evolution

X Li, Y Zhao, Z Wu, W Zhang, RH Li… - Proceedings of the AAAI …, 2024‏ - ojs.aaai.org
With the rapid advancement of AI applications, the growing needs for data privacy and
model robustness have highlighted the importance of machine unlearning, especially in …

Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition

H Tian, Y Zhang, H Wu, X Ma, Y Li - Neurocomputing, 2024‏ - Elsevier
Skeleton-based action recognition has attracted increasing interest in recent years. With the
flexibility of modeling long-range dependency of joints, the self-attention module has served …

Partitioning message passing for graph fraud detection

W Zhuo, Z Liu, B Hooi, B He, G Tan, R Fathony… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Label imbalance and homophily-heterophily mixture are the fundamental problems
encountered when applying Graph Neural Networks (GNNs) to Graph Fraud Detection …

Multiresolution graph transformers and wavelet positional encoding for learning long-range and hierarchical structures

NK Ngo, TS Hy, R Kondor - The Journal of Chemical Physics, 2023‏ - pubs.aip.org
Contemporary graph learning algorithms are not well-suited for large molecules since they
do not consider the hierarchical interactions among the atoms, which are essential to …