A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs

Lin, Lequan; Gao, Junbin

doi:10.1109/icassp49357.2023.10097148

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…com/ super ca729/ pL-UFG. Lastly, it is worth noting that our proposed method has the potential to be applied to the graph learning task other than node classification such as graph level classification (pooling) [60] and link prediction [31]. Although we have yet to delve into these tasks, we believe that by assigning some simple manipulations to our methods, such as deploying the readout function for graph pooling or computing the log-likelihood for graph link prediction, our method is capable of handling these tasks.…”

Section: Methodsmentioning

confidence: 99%

Enhancing framelet GCNs with generalized p-Laplacian regularization

Shao,

Shi,

Han

et al. 2023

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

Graph neural networks (GNNs) have achieved remarkable results for various graph learning tasks. However, one of the recent challenges for GNNs is to adapt to different types of graph inputs, such as heterophilic graph datasets in which linked nodes are more likely to contain a different class of labels and features. Accordingly, an ideal GNN model should adaptively accommodate all types of graph datasets with different labeling distributions. In this paper, we tackle this challenge by proposing a regularization framework on graph framelet with the regularizer induced from graph p-Laplacian. By adjusting the value of p, the p-Laplacian based regularizer restricts the solution space of graph framelet into the desirable region based on the graph homophilic features. We propose an algorithm to effectively solve a more generalized regularization problem and prove that the algorithm imposes a (p-Laplacian based) spectral convolution and diagonal scaling operation to the framelet filtered node features. Furthermore, we analyze the denoising power of the proposed model and compare it with the predefined framelet denoising regularizer. Finally, we conduct empirical studies to show the prediction power of the proposed model in both homophily undirect and heterophily direct graphs with and without noises. Our proposed model shows significant improvements compared to multiple baselines, and this suggests the effectiveness of combining graph framelet and p-Laplacian.

show abstract

Section: Methodsmentioning

confidence: 99%