A graph foundation model with text-encoded meta-relations and a mixture of context-adaptive transformers improves accuracy across homogeneous and heterogeneous text-attributed graphs.
Link prediction on latent heterogeneous graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs
A graph foundation model with text-encoded meta-relations and a mixture of context-adaptive transformers improves accuracy across homogeneous and heterogeneous text-attributed graphs.