Pieceformer, a self-supervised hybrid graph transformer with partitioned training, improves graph similarity ranking for VLSI designs by 24.9% MAE over a GIN baseline and enables up to 89% faster KL partitioning.
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
REJECT 1representative citing papers
citing papers explorer
-
Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI
Pieceformer, a self-supervised hybrid graph transformer with partitioned training, improves graph similarity ranking for VLSI designs by 24.9% MAE over a GIN baseline and enables up to 89% faster KL partitioning.