AutoFGNN: A Framework for Extracting All Frequency Information from Large-Scale Graphs

Qi Zhang, Yanfeng Sun, Jipeng Guo, Shaofan Wang, Jinghua Li, Junbin Gao, Baocai Yin

Abstract

As a powerful model for deep learning on graph-structured data, the scalability limitation of Graph Neural Networks (GNNs) are receiving increasing attention. To tackle this limitation, two categories of scalable GNNs have been proposed: sampling-based and model simplification methods. However, sampling-based methods suffer from high communication costs and poor performance due to the sampling process. Conversely, existing model simplification methods only rely on parameter-free feature propagation, disregarding its spectral properties. Consequently, these methods can only capture low-frequency information while disregarding valuable middle- and high-frequency information. This paper proposes Automatic Filtering Graph Neural Networks (AutoFGNN), a framework that can extract all frequency information from large-scale graphs. AutoFGNN employs parameter-free low-, middle-, and high-pass filters, which extract the corresponding information for all nodes without introducing parameters. To merge the extracted features, a trainable transformer-based information fusion module is utilized, enabling AutoFGNN to be trained in a mini-batch manner and ensuring scalability for large-scale graphs. Experimental results show that AutoFGNN outperforms existing methods on various scale graphs.
BibTeX
@inproceedings{zhang2024autofgnn,
  author = {Qi Zhang and Yanfeng Sun and Jipeng Guo and Shaofan Wang and Jinghua Li and Junbin Gao and Baocai Yin},
  title = {{AutoFGNN: A Framework for Extracting All Frequency Information from Large-Scale Graphs}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2024},
  doi = {10.1109/icassp48485.2024.10448287},
}

Loading related content...

Figure