用自监督方法学习电路单元向量表示，提升模型对单元语义的捕捉能力。
Learning Library Cell Representations in Vector Space
- 从Liberty文件自动提取训练数据，免去人工标注成本。
- 通过向量运算发现单元间逻辑关系，如BUF - INV + NAND ≈ AND。
- 适用于标签数据少的电路学习任务，尤其适合芯片设计场景。
我们提出 Lib2Vec，一种新颖的自监督框架，可高效学习电路单元的有意义向量表示，使机器学习模型能够捕捉单元的关键语义。该框架包含三个核心组件：(1) 自动生成规律性测试，定量评估单元表示是否反映单元间关系；(2) 从 Liberty 文件系统性提取训练数据的自监督学习方案，无需昂贵的人工标注；(3) 基于注意力机制的模型架构，支持不同引脚数量，并实现属性特定的单元与弧嵌入。实验表明，Lib2Vec 能有效捕捉功能和电气相似性。线性代数操作显示，向量关系如 vector(BUF) - vector(INV) + vector(NAND) ~ vector(AND) 具有实际意义，体现其精细表示能力。此外，该框架显著提升下游电路学习应用性能，尤其在标注数据稀缺时表现突出。
原文摘要 · Abstract (English)
We propose Lib2Vec, a novel self-supervised framework to efficiently learn meaningful vector representations of library cells, enabling ML models to capture essential cell semantics. The framework comprises three key components: (1) an automated method for generating regularity tests to quantitatively evaluate how well cell representations reflect inter-cell relationships; (2) a self-supervised learning scheme that systematically extracts training data from Liberty files, removing the need for costly labeling; and (3) an attention-based model architecture that accommodates various pin counts and enables the creation of property-specific cell and arc embeddings. Experimental results demonstrate that Lib2Vec effectively captures functional and electrical similarities. Moreover, linear algebraic operations on cell vectors reveal meaningful relationships, such as vector(BUF) - vector(INV) + vector(NAND) ~ vector(AND), showcasing the framework's nuanced representation capabilities. Lib2Vec also enhances downstream circuit learning applications, especially when labeled data is scarce.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。