<ul data-eligibleForWebStory="false"><li>Graph representation learning is utilized to extract features from graph-structured data like analog/mixed-signal (AMS) circuits.</li><li>CircuitGPS, a few-shot learning method, is introduced for predicting parasitic effects in AMS circuits.</li><li>The method involves pre-training on link prediction and fine-tuning on edge regression, utilizing a hybrid graph Transformer and positional encoding.</li><li>CircuitGPS enhances coupling existence accuracy by at least 20% and reduces capacitance estimation MAE by at least 0.067, showcasing scalability and applicability to diverse AMS circuit designs.</li></ul>

Few-shot Learning on AMS Circuits and Its Application to Parasitic Capacitance Prediction

Discover more