Fast and Accurate RFIC Performance Prediction via Pin Level Graph Neural Networks and Probabilistic Flow

--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. T o 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 3.14 while using 2.24 fewer training samples compared to prior work, demonstrating the method's effectiveness for rapid and accurate RF circuit design automation. Index T erms--Graph neural network (GNN), RF circuit modeling, masked autoregressive flow (MAF), electronic design automation (EDA), machine learning. With the growing importance of modern wireless systems (e.g., the Internet of Things [1], 5G [2] RADAR [3], and Li-DAR [4]) accurate modeling and optimization of RF integrated circuits (RFICs) is more critical than ever. The performance of key building blocks of such systems, ranging from power amplifiers (P A) to transmitters, directly affects the fidelity, efficiency, and robustness of modern systems. This work was supported in part by the CogniSense: Center on Cognitive Multi-spectral Sensors, one of seven centers in Joint University Microelectronics Program (JUMP) 2.0, a Semiconductor Research Corporation (SRC) program sponsored by the Defense Advance Research Project Agency (DARP A). While highly accurate, traditional simulators (e.g., SPICE, ADS, ANSYS) are computationally expensive, especially when sweeping process-voltage-temperature (PVT) corners or performing extensive design-space exploration.