Lightweight autoregressive graph generation model uses structure-guided ordering for efficient serialization and two-phase training to boost novelty while maintaining validity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
Lightweight autoregressive graph generation model uses structure-guided ordering for efficient serialization and two-phase training to boost novelty while maintaining validity.