A masked language model fine-tuned on metapath-derived text and cloze-style task templates transfers across heterogeneous graph datasets better than HGNN and LLM baselines, though link prediction results are compromised by test-edge leakage.
Heterogeneous graph contrastive learning for recommendation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SI 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Masked Language Models are Good Heterogeneous Graph Generalizers
A masked language model fine-tuned on metapath-derived text and cloze-style task templates transfers across heterogeneous graph datasets better than HGNN and LLM baselines, though link prediction results are compromised by test-edge leakage.