Lanze Zhang, Yijun Gu*, Jingjie Peng
CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.2, pp. 1701-1731, 2024, DOI:10.32604/cmes.2023.045129
Abstract Graph Neural Networks (GNNs) play a significant role in tasks related to homophilic graphs. Traditional GNNs, based on the assumption of homophily, employ low-pass filters for neighboring nodes to achieve information aggregation and embedding. However, in heterophilic graphs, nodes from different categories often establish connections, while nodes of the same category are located further apart in the graph topology. This characteristic poses challenges to traditional GNNs, leading to issues of “distant node modeling deficiency” and “failure of the homophily assumption”. In response, this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks (SFA-HGNN), which integrates adaptive embedding mechanisms for… More >
Login
Register
