Graph tokenizations for Transformers induce distinct depth regimes with proven separations and impossibility results for converting between them at limited depth.
Proceedings of the 34th International Conference on Neural Information Processing Systems , articleno =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers
Graph tokenizations for Transformers induce distinct depth regimes with proven separations and impossibility results for converting between them at limited depth.