Transformer self-attention is message passing on a complete graph, making Transformers a special case of graph neural networks.
Title resolution pending
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
-
Transformers are Graph Neural Networks
Transformer self-attention is message passing on a complete graph, making Transformers a special case of graph neural networks.