# Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation

arXiv: https://arxiv.org/abs/2011.13522 · HTML: https://mlsanity.com/paper/2011.13522/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Position: Topological Deep Learning is the New Frontier for Relational Learning](https://mlsanity.com/paper/2402.08871/) (2024)
- [DeepGate: Learning Neural Representations of Logic Gates](https://mlsanity.com/paper/2111.14616/) (2021)
- [DE-HNN: An effective neural model for Circuit Netlist representation](https://mlsanity.com/paper/2404.00477/) (2024)
- [PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling](https://mlsanity.com/paper/2403.00012/) (2024)
- [Graph Neural Networks: A Powerful and Versatile Tool for Advancing Design, Reliability, and Security of ICs](https://mlsanity.com/paper/2211.16495/) (2022)
- [The Dark Side: Security Concerns in Machine Learning for EDA](https://mlsanity.com/paper/2203.10597/) (2022)
- [Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI](https://mlsanity.com/paper/2506.15907/) (2025)
- [Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network](https://mlsanity.com/paper/2508.11991/) (2025)

## Abstract (arXiv)

Net length is a key proxy metric for optimizing timing and power across various stages of a standard digital design flow. However, the bulk of net length information is not available until cell placement, and hence it is a significant challenge to explicitly consider net length optimization in design stages prior to placement, such as logic synthesis. This work addresses this challenge by proposing a graph attention network method with customization, called Net2, to estimate individual net length before cell placement. Its accuracy-oriented version Net2a achieves about 15% better accuracy than several previous works in identifying both long nets and long critical paths. Its fast version Net2f is more than 1000 times faster than placement while still outperforms previous works and other neural network techniques in terms of various accuracy metrics.