GL-Fusion merges message passing, full-text cross-attention, and twin GNN/LLM prediction heads into one model, reporting state-of-the-art results on ogbn-arxiv and ogbg-code2.
Some parameters are loaded from pretrained LLM
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model
GL-Fusion merges message passing, full-text cross-attention, and twin GNN/LLM prediction heads into one model, reporting state-of-the-art results on ogbn-arxiv and ogbg-code2.