Fast and Accurate RFIC Performance Prediction via Pin Level Graph Neural Networks and Probabilistic Flow
This work addresses the problem of rapid and accurate RF circuit design automation for engineers, offering a data-efficient solution that is incremental in improving existing ML surrogates.
The paper tackles the challenge of predicting active RF circuit performance by proposing a lightweight graph neural network model with probabilistic flow, achieving high accuracy with sMAPE and MRE averaging 2.40% and 2.91%, respectively, and improving MRE by 3.14x while using 2.24x fewer training samples compared to prior work.
Accurately predicting the performance of active radio frequency (RF) circuits is essential for modern wireless systems but remains challenging due to highly nonlinear, layout-sensitive behavior and the high computational cost of traditional simulation tools. Existing machine learning (ML) surrogates often require large datasets to generalize across various topologies or to accurately model skewed and multi-modal performance metrics. In this work, a lightweight, data-efficient, and topology-aware graph neural network (GNN) model is proposed for predicting key performance metrics of multiple topologies of active RF circuits such as low noise amplifiers (LNAs), mixers, voltage-controlled oscillators (VCOs), and PAs. To capture transistor-level symmetry and preserve fine-grained connectivity details, circuits are modeled at the device-terminal level, enabling scalable message passing while reducing data requirements. Masked autoregressive flow (MAF) output heads are incorporated to improve robustness in modeling complex target distributions. Experiments on datasets demonstrate high prediction accuracy, with symmetric mean absolute percentage error (sMAPE) and mean relative error (MRE) averaging 2.40% and 2.91%, respectively. Owing to the pin-level conversion of circuit to graph and ML architecture robust to modeling complex densities of RF metrics, the MRE is improved by 3.14x while using 2.24x fewer training samples compared to prior work, demonstrating the method's effectiveness for rapid and accurate RF circuit design automation.