HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily

ArXi:2605.04594v1 Announce Type: cross Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard heterogeneous graph neural networks that aggregate messages along metapaths or meta-relations primarily based on feature similarity can propagate misleading information, since feature similarity may be misaligned with underlying relational semantics.