Equivariant Matrix Function Neural Networks. (arXiv:2310.10434v2 [stat.ML] UPDATED)

Graph Neural Networks (GNNs), especially message-passing neural networks
(MPNNs), have emerged as powerful architectures for learning on graphs in
diverse applications. However, MPNNs face challenges when modeling non-local
interactions in graphs such as large conjugated molecules, and social networks
due to oversmoothing and oversquashing. Although Spectral GNNs and traditional
neural networks such as recurrent neural networks and transformers mitigate
these challenges, they often lack generalizability, or fail to capture detailed
structural relationships or symmetries in the data. To address these …

applications architectures arxiv challenges diverse diverse applications face function gnns graph graph neural networks graphs interactions matrix modeling molecules networks neural networks social social networks stat.ml