Abstract
Wavelet-based graph neural networks have received increasing attention in the node classification task. Existing graph wavelet-based approaches, however, are not applicable to arbitrary graphs as they use predefined wavelet filters with built-in homophilic assumptions and disregard heterophily. Recent studies attempted to address this issue through a wavelet lifting transform, which requires a bipartite graph, therefore altering the graph topology and leading to undesirable wavelet filters. This paper proposes a generalized adaptive graph wavelet network that preserves the graph topology through computational trees while implementing the lifting scheme on arbitrary graphs. Moreover, this locally defined lifting scheme integrates both high-pass and low-pass frequency components to further enhance feature representation. Finally, we benchmark our model using nine homophilic and heterophilic datasets, and the results demonstrate the effectiveness of our method.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.