# Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI

arXiv: https://arxiv.org/abs/2506.15907 · HTML: https://mlsanity.com/paper/2506.15907/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Chip Placement with Deep Reinforcement Learning](https://mlsanity.com/paper/2004.10746/) (2020)
- [Understanding Softmax Confidence and Uncertainty](https://mlsanity.com/paper/2106.04972/) (2021)
- [Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers](https://mlsanity.com/paper/2006.03555/) (2020)
- [Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation](https://mlsanity.com/paper/2011.13522/) (2020)
- [NVCell: Standard Cell Layout in Advanced Technology Nodes with Reinforcement Learning](https://mlsanity.com/paper/2107.07044/) (2021)
- [Relative Hausdorff Distance for Network Analysis](https://mlsanity.com/paper/1906.04936/) (2019)
- [Network mutual information measures for graph similarity](https://mlsanity.com/paper/2405.05177/) (2024)

## Abstract (arXiv)

Accurate graph similarity is critical for knowledge transfer in VLSI design, enabling the reuse of prior solutions to reduce engineering effort and turnaround time. We propose Pieceformer, a scalable, self-supervised similarity assessment framework, equipped with a hybrid message-passing and graph transformer encoder. To address transformer scalability, we incorporate a linear transformer backbone and introduce a partitioned training pipeline for efficient memory and parallelism management. Evaluations on synthetic and real-world CircuitNet datasets show that Pieceformer reduces mean absolute error (MAE) by 24.9% over the baseline and is the only method to correctly cluster all real-world design groups. We further demonstrate the practical usage of our model through a case study on a partitioning task, achieving up to 89% runtime reduction. These results validate the framework's effectiveness for scalable, unbiased design reuse in modern VLSI systems.