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

TL;DR

This paper introduces CircuitGPS, a few-shot graph learning method for parasitic capacitance prediction in AMS circuits, addressing data scarcity and enabling accurate, scalable predictions with minimal training data.

Contribution

The paper presents a novel few-shot learning approach using graph Transformers and subgraph sampling for parasitic effect prediction in AMS circuits, with improved accuracy and scalability.

Findings

At least 20% improvement in coupling existence accuracy

At least 0.067 reduction in MAE of capacitance estimation

Effective zero-shot learning for diverse AMS circuit designs

Abstract

Graph representation learning is a powerful method to extract features from graph-structured data, such as analog/mixed-signal (AMS) circuits. However, training deep learning models for AMS designs is severely limited by the scarcity of integrated circuit design data. In this work, we present CircuitGPS, a few-shot learning method for parasitic effect prediction in AMS circuits. The circuit netlist is represented as a heterogeneous graph, with the coupling capacitance modeled as a link. CircuitGPS is pre-trained on link prediction and fine-tuned on edge regression. The proposed method starts with a small-hop sampling technique that converts a link or a node into a subgraph. Then, the subgraph embeddings are learned with a hybrid graph Transformer. Additionally, CircuitGPS integrates a low-cost positional encoding that summarizes the positional and structural information of the sampled subgraph. CircuitGPS improves the accuracy of coupling existence by at least 20\% and reduces the MAE of capacitance estimation by at least 0.067 compared to existing methods. Our method demonstrates strong inherent scalability, enabling direct application to diverse AMS circuit designs through zero-shot learning. Furthermore, the ablation studies provide valuable insights into graph models for representation learning.