Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Node-oriented Spectral Filtering for Graph Neural Networks

About

Graph neural networks (GNNs) have shown remarkable performance on homophilic graph data while being far less impressive when handling non-homophilic graph data due to the inherent low-pass filtering property of GNNs. In general, since real-world graphs are often complex mixtures of diverse subgraph patterns, learning a universal spectral filter on the graph from the global perspective as in most current works may still suffer from great difficulty in adapting to the variation of local patterns. On the basis of the theoretical analysis of local patterns, we rethink the existing spectral filtering methods and propose the node-oriented spectral filtering for graph neural network (namely NFGNN). By estimating the node-oriented spectral filter for each node, NFGNN is provided with the capability of precise local node positioning via the generalized translated operator, thus discriminating the variations of local homophily patterns adaptively. Meanwhile, the utilization of re-parameterization brings a good trade-off between global consistency and local sensibility for learning the node-oriented spectral filters. Furthermore, we theoretically analyze the localization property of NFGNN, demonstrating that the signal after adaptive filtering is still positioned around the corresponding node. Extensive experimental results demonstrate that the proposed NFGNN achieves more favorable performance.

Shuai Zheng, Zhenfeng Zhu, Zhizhe Liu, Youru Li, Yao Zhao• 2022

Related benchmarks

TaskDatasetResultRank
Node ClassificationRoman-Empire
Accuracy75.36
327
Node ClassificationAmazon Photo
Accuracy80.8
313
Node Classificationamazon-ratings
Accuracy47.99
309
Node ClassificationAmazon Computers
Accuracy58.51
167
Node ClassificationCoauthor CS
Accuracy94.72
158
Node ClassificationOGBN-Products
Accuracy81.02
128
Node ClassificationPhoto (test)
Mean Accuracy92.51
125
Node ClassificationComputers (test)
Mean Accuracy86.91
109
Node ClassificationCoauthor Physics
Accuracy96.94
104
Node ClassificationCora (semi-supervised)
Accuracy77.69
103
Showing 10 of 52 rows

Other info

Follow for update